Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
Greetings and welcome to lisp @ Boston. Are you going to be working in the Cambridge office? And out of curiosity do you use lisp in your optimization research?
On Sun, Jul 28, 2019, 7:27 AM Masataro Asai guicho2.71828@gmail.com wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Correct. MIT-IBM Waton AI Lab. I do use lisp!
2019年7月28日(日) 9:31 Jonathan Godbout jgodbou@gmail.com:
Greetings and welcome to lisp @ Boston. Are you going to be working in the Cambridge office? And out of curiosity do you use lisp in your optimization research?
On Sun, Jul 28, 2019, 7:27 AM Masataro Asai guicho2.71828@gmail.com wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
It should be updated: https://common-lisp.net/project/boston-lisp/
On Mon, Jul 29, 2019 at 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com
wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Please do not do it yet --- I should ask my boss if I can give a talk. (the abstract is almost a copy from my paper abstract, to avoid issues)
Jonathan Godbout wrote:
It should be updated: https://common-lisp.net/project/boston-lisp/
On Mon, Jul 29, 2019 at 7:33 AM Masataro Asai <guicho2.71828@gmail.com mailto:guicho2.71828@gmail.com> wrote:
Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more. For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, we can meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb about yourself, another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/
Ok, It seems the new boss at Cambridge seems to be much more liberal and open-minded than the manager I had in Japan. I got an approval. Please go ahead -- update the info. Thank you.
On Tue, Jul 30, 2019 at 5:44 PM Masataro Asai guicho2.71828@gmail.com wrote:
Please do not do it yet --- I should ask my boss if I can give a talk. (the abstract is almost a copy from my paper abstract, to avoid issues)
Jonathan Godbout wrote:
It should be updated: https://common-lisp.net/project/boston-lisp/
On Mon, Jul 29, 2019 at 7:33 AM Masataro Asai <guicho2.71828@gmail.com mailto:guicho2.71828@gmail.com> wrote:
Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more ofan
academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let megive
a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert inheuristic
graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more. For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning hasachieved
significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolicsystems
such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only anunlabeled
set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a planto
the goal state in a symbolic latent space and returns a visualizedplan
execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, we can meet fordinner
> afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb about yourself, another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much.
Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting.
On Mon, Jul 29, 2019, 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com
wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space".
2019年8月1日(木) 16:19 Jeff Read bitwize@gmail.com:
Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much.
Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting.
On Mon, Jul 29, 2019, 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com
wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT.
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org
On Thu, Aug 1, 2019, 20:34 Guicho 271828 guicho2.71828@gmail.com wrote:
I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space".
2019年8月1日(木) 16:19 Jeff Read bitwize@gmail.com:
Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much.
Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting.
On Mon, Jul 29, 2019, 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent perspiration. — Thomas Alva Edison
On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai guicho2.71828@gmail.com
wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré fahree@gmail.com wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT.
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org
On Thu, Aug 1, 2019, 20:34 Guicho 271828 guicho2.71828@gmail.com wrote:
I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space".
2019年8月1日(木) 16:19 Jeff Read bitwize@gmail.com:
Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much.
Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting.
On Mon, Jul 29, 2019, 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent
perspiration.
— Thomas Alva EdisonOn Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <
guicho2.71828@gmail.com> wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
What kind of information is needed? BTW, my company also seems to let me use a floor in our building. Perhaps from the next time, if it is recurring.
Masataro
Jonathan Godbout wrote:
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré <fahree@gmail.com mailto:fahree@gmail.com> wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT. —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org On Thu, Aug 1, 2019, 20:34 Guicho 271828 <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space". 2019年8月1日(木) 16:19 Jeff Read <bitwize@gmail.com <mailto:bitwize@gmail.com>>: Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much. Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680 It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting. On Mon, Jul 29, 2019, 7:33 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more. For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, we can meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb about yourself, another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/
I am waaaaay too busy with legal issues concerning my startup at the moment.
Will anyone on this mailing-list assume editorship, at least temporarily, of the boston-lisp.common-lisp.net page, to update it?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org C is a DSL for turning low-level byte arrays into security advisories.
On Mon, Aug 5, 2019 at 1:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
What kind of information is needed? BTW, my company also seems to let me use a floor in our building. Perhaps from the next time, if it is recurring.
Masataro
Jonathan Godbout wrote:
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré <fahree@gmail.com mailto:fahree@gmail.com> wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT. —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org On Thu, Aug 1, 2019, 20:34 Guicho 271828 <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space". 2019年8月1日(木) 16:19 Jeff Read <bitwize@gmail.com <mailto:bitwize@gmail.com>>: Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much. Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680 It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting. On Mon, Jul 29, 2019, 7:33 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more. For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, we can meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb about yourself, another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Fare, I'll make the change. Alec, there will be, it will be at Google: 355 Main St, Cambridge, MA 02142 Anyone who wants to go should email me directly, and we'll meet in the Google lobby around 6:45 so we can start at 7, assuming 7 is good for everyone?
On Mon, Aug 5, 2019 at 2:20 AM Faré fahree@gmail.com wrote:
I am waaaaay too busy with legal issues concerning my startup at the moment.
Will anyone on this mailing-list assume editorship, at least temporarily, of the boston-lisp.common-lisp.net page, to update it?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org C is a DSL for turning low-level byte arrays into security advisories.
On Mon, Aug 5, 2019 at 1:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
What kind of information is needed? BTW, my company also seems to let me use a floor in our building. Perhaps from the next time, if it is recurring.
Masataro
Jonathan Godbout wrote:
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré <fahree@gmail.com mailto:fahree@gmail.com> wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT. —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org On Thu, Aug 1, 2019, 20:34 Guicho 271828 <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space". 2019年8月1日(木) 16:19 Jeff Read <bitwize@gmail.com <mailto:bitwize@gmail.com>>: Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much. Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source:https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting. On Mon, Jul 29, 2019, 7:33 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) andmore.
For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, we can meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb about yourself, another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Hi all,
I think we need to update the website ASAP & announce it or people will not be able to sort out the schedule. I don't know the dominant population in this group (does it also include Clojure, scheme?) but I am happy if more people come even from the non-CL lisp background.
Masataro
On Fri, Aug 9, 2019 at 10:10 PM Jonathan Godbout jgodbou@gmail.com wrote:
Fare, I'll make the change. Alec, there will be, it will be at Google: 355 Main St, Cambridge, MA 02142 Anyone who wants to go should email me directly, and we'll meet in the Google lobby around 6:45 so we can start at 7, assuming 7 is good for everyone?
On Mon, Aug 5, 2019 at 2:20 AM Faré fahree@gmail.com wrote:
I am waaaaay too busy with legal issues concerning my startup at the moment.
Will anyone on this mailing-list assume editorship, at least temporarily, of the boston-lisp.common-lisp.net page, to update it?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org C is a DSL for turning low-level byte arrays into security advisories.
On Mon, Aug 5, 2019 at 1:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
What kind of information is needed? BTW, my company also seems to let me use a floor in our building. Perhaps from the next time, if it is recurring.
Masataro
Jonathan Godbout wrote:
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré <fahree@gmail.com mailto:fahree@gmail.com> wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within thetime
frame. Otherwise I can get a room at MIT. —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org On Thu, Aug 1, 2019, 20:34 Guicho 271828 <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planningin
Deep Latent Space". 2019年8月1日(木) 16:19 Jeff Read <bitwize@gmail.com <mailto:bitwize@gmail.com>>: Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much. Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from thecon
entirely for proposing it. Source:https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting. On Mon, Jul 29, 2019, 7:33 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japanfor
quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling,also
known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) andmore.
For the talk: Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, wecan
meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb aboutyourself,
another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
Yip, the site is updated on Gitlab, just working with common-lisp.net to be able to send it to them and make the changes live.
On Tue, Aug 13, 2019 at 9:31 AM Guicho 271828 guicho2.71828@gmail.com wrote:
Hi all,
I think we need to update the website ASAP & announce it or people will not be able to sort out the schedule. I don't know the dominant population in this group (does it also include Clojure, scheme?) but I am happy if more people come even from the non-CL lisp background.
Masataro
On Fri, Aug 9, 2019 at 10:10 PM Jonathan Godbout jgodbou@gmail.com wrote:
Fare, I'll make the change. Alec, there will be, it will be at Google: 355 Main St, Cambridge, MA 02142 Anyone who wants to go should email me directly, and we'll meet in the Google lobby around 6:45 so we can start at 7, assuming 7 is good for everyone?
On Mon, Aug 5, 2019 at 2:20 AM Faré fahree@gmail.com wrote:
I am waaaaay too busy with legal issues concerning my startup at the moment.
Will anyone on this mailing-list assume editorship, at least temporarily, of the boston-lisp.common-lisp.net page, to update it?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org C is a DSL for turning low-level byte arrays into security advisories.
On Mon, Aug 5, 2019 at 1:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
What kind of information is needed? BTW, my company also seems to let me use a floor in our building. Perhaps from the next time, if it is recurring.
Masataro
Jonathan Godbout wrote:
All I need is a list of people, I'll have to register them manually. Also could we update https://common-lisp.net/project/boston-lisp/
On Fri, Aug 2, 2019 at 6:31 AM Faré <fahree@gmail.com mailto:fahree@gmail.com> wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within thetime
frame. Otherwise I can get a room at MIT. —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org On Thu, Aug 1, 2019, 20:34 Guicho 271828 <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planningin
Deep Latent Space". 2019年8月1日(木) 16:19 Jeff Read <bitwize@gmail.com <mailto:bitwize@gmail.com>>: Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're stillon
for August 15 I would love to attend as I think I would learn much. Bikeshed issue: You may wish to consider revising thetitle
of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from thecon
entirely for proposing it. Source:https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it,and
relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting. On Mon, Jul 29, 2019, 7:33 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.comwrote: Thank you for the invitation :) August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japanfor
quite a while...) Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine. Blurb meaning the short description / abstract of the talk? Let me give a try... For myself: Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling,also
known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) andmore.
For the talk: Title: Make Symbols Great Again!: ClassicalPDDL/STRIPS
Planning in Deep Latent Space Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, anunsupervised
architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returnsa
visualized plan execution. In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions. Regards Masataro Faré wrote: > Congratulations! > > Let's summon a Boston Lisp Meeting to greet you. > How about Thursday August 15th at 1800? > > I'll try to reserve a room at MIT. Either way, wecan
meet for dinner > afterwards. > > Can you give a speech on some topic of your choice? Otherwise is there > any other candidate? > Can you give me a one-paragraph blurb aboutyourself,
another one > about your topic? > > —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org > Genius is one percent inspiration and ninety-nine percent perspiration. > — Thomas Alva Edison > > On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com>> wrote: >> >> Dear all, >> >> I just moved to Boston yesterday. 5yr assignment. >> Thanks >> >> -- >> Masataro Asai Ph.D >> >> Research Staff Member >> IBM Research >> >> Tel: +81-44-856-9009 >> Mobile: +81-50-5534-1357 >> Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> >> Website: http://guicho271828.github.io/ >> -- Masataro Asai Ph.D Research Staff Member IBM Research Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com <mailto:guicho2.71828@gmail.com> Website: http://guicho271828.github.io/-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai, Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357
Website(private): http://guicho271828.github.io/
Is there going to be a meeting on August 15 and how to get there/register?
Regards, Alec Segal
On Fri, Aug 2, 2019 at 6:31 AM Faré fahree@gmail.com wrote:
Jon Godbout is offering us a space at Google for the meeting. I believe this means advance registration required. Unless someone strongly objects, I believe this is the right choice within the time frame. Otherwise I can get a room at MIT.
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• http://fare.tunes.org
On Thu, Aug 1, 2019, 20:34 Guicho 271828 guicho2.71828@gmail.com wrote:
I see, maybe it is safer to avoid that title in the US. Please make the title just as "Classical PDDL/STRIPS Planning in Deep Latent Space".
2019年8月1日(木) 16:19 Jeff Read bitwize@gmail.com:
Color me intrigued -- it certainly does seem interesting, and potentially unifies symbol and logic based GOFAI with the "throw more statistics at the problem" school that currently encompasses "AI" as a buzzword. If we're still on for August 15 I would love to attend as I think I would learn much.
Bikeshed issue: You may wish to consider revising the title of your talk. "Make X great again" is considered "normalizing hate speech" and very offensive, therefore unacceptable by 2019 professional standards. Major open-source conferences will reject a talk proposal with such a title, and some may preëmptively ban you from the con entirely for proposing it. Source: https://mobile.twitter.com/aurynn/status/1128053124323655680
It may not be an issue among us (Faré may even like it, and relish a twist of the old knife), but among less laid-back groups and conferences it can be severely career-limiting.
On Mon, Jul 29, 2019, 7:33 AM Masataro Asai guicho2.71828@gmail.com wrote:
Thank you for the invitation :)
August 15th should work, but I need to confirm the schedule in the company, which I cannot check now until I complete the onboarding process of US IBM (although I have been in IBM Japan for quite a while...)
Will they be posted on any sort of MIT bulletin board? Is it more of an academic event? That might need a permission from the manager. For an informal meeting it should be fine.
Blurb meaning the short description / abstract of the talk? Let me give a try...
For myself:
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of experience in Common Lisp, who received a Ph.D in Artificial Intelligence from the University of Tokyo. He is an expert in heuristic graph search and automated planning and scheduling, also known as AI Planning, with publications records on top AI conferences e.g. AAAI, IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical computation library NUMCL (which got 400 stars) and more.
For the talk:
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep Latent Space
Domain-independent classical planners require the symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We introduce LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of images representing the initial and the goal states (planning inputs), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.
In the talk, we also survey the recent progress in the related fields and also informally talk about my future ambitions.
Regards Masataro
Faré wrote:
Congratulations!
Let's summon a Boston Lisp Meeting to greet you. How about Thursday August 15th at 1800?
I'll try to reserve a room at MIT. Either way, we can meet for dinner afterwards.
Can you give a speech on some topic of your choice? Otherwise is there any other candidate? Can you give me a one-paragraph blurb about yourself, another one about your topic?
—♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics•
Genius is one percent inspiration and ninety-nine percent
perspiration.
— Thomas Alva EdisonOn Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <
guicho2.71828@gmail.com> wrote:
Dear all,
I just moved to Boston yesterday. 5yr assignment. Thanks
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-- Masataro Asai Ph.D
Research Staff Member IBM Research
Tel: +81-44-856-9009 Mobile: +81-50-5534-1357 Mail: guicho2.71828@gmail.com Website: http://guicho271828.github.io/
-
Alec Segal -
Faré -
Guicho 271828 -
Jeff Read -
Jonathan Godbout -
Masataro Asai