<div dir="ltr">It should be updated: <a href="https://common-lisp.net/project/boston-lisp/">https://common-lisp.net/project/boston-lisp/</a><div><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Jul 29, 2019 at 7:33 AM Masataro Asai <<a href="mailto:guicho2.71828@gmail.com">guicho2.71828@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Thank you for the invitation :)<br>
<br>
August 15th should work, but I need to confirm the schedule in the <br>
company, which I cannot check now until I complete the onboarding <br>
process of US IBM (although I have been in IBM Japan for quite a while...)<br>
<br>
Will they be posted on any sort of MIT bulletin board? Is it more of an <br>
academic event? That might need a permission from the manager. For an <br>
informal meeting it should be fine.<br>
<br>
Blurb meaning the short description / abstract of the talk? Let me give <br>
a try...<br>
<br>
For myself:<br>
<br>
Masataro Asai, aka guicho271828, is a Lisp hacker with 11 years of <br>
experience in Common Lisp, who received a Ph.D in Artificial <br>
Intelligence from the University of Tokyo. He is an expert in heuristic <br>
graph search and automated planning and scheduling, also known as AI <br>
Planning, with publications records on top AI conferences e.g. AAAI, <br>
IJCAI, ICAPS. Author of a fast pattern match library Trivia, a numerical <br>
computation library NUMCL (which got 400 stars) and more.<br>
<br>
For the talk:<br>
<br>
Title: Make Symbols Great Again!: Classical PDDL/STRIPS Planning in Deep <br>
Latent Space<br>
<br>
Domain-independent classical planners require the symbolic models of the <br>
problem domain and instance as input, resulting in a knowledge <br>
acquisition bottleneck. Meanwhile, although deep learning has achieved <br>
significant success in many fields, the knowledge is encoded in a <br>
subsymbolic representation which is incompatible with symbolic systems <br>
such as planners. We introduce LatPlan, an unsupervised architecture <br>
combining deep learning and classical planning. Given only an unlabeled <br>
set of image pairs showing a subset of transitions allowed in the <br>
environment (training inputs), and a pair of images representing the <br>
initial and the goal states (planning inputs), LatPlan finds a plan to <br>
the goal state in a symbolic latent space and returns a visualized plan <br>
execution.<br>
<br>
In the talk, we also survey the recent progress in the related fields <br>
and also informally talk about my future ambitions.<br>
<br>
Regards<br>
Masataro<br>
<br>
<br>
Faré wrote:<br>
> Congratulations!<br>
> <br>
> Let's summon a Boston Lisp Meeting to greet you.<br>
> How about Thursday August 15th at 1800?<br>
> <br>
> I'll try to reserve a room at MIT. Either way, we can meet for dinner<br>
> afterwards.<br>
> <br>
> Can you give a speech on some topic of your choice? Otherwise is there<br>
> any other candidate?<br>
> Can you give me a one-paragraph blurb about yourself, another one<br>
> about your topic?<br>
> <br>
> —♯ƒ • François-René ÐVB Rideau •Reflection&Cybernethics• <a href="http://fare.tunes.org" rel="noreferrer" target="_blank">http://fare.tunes.org</a><br>
> Genius is one percent inspiration and ninety-nine percent perspiration.<br>
> — Thomas Alva Edison<br>
> <br>
> On Sun, Jul 28, 2019 at 7:27 AM Masataro Asai <<a href="mailto:guicho2.71828@gmail.com" target="_blank">guicho2.71828@gmail.com</a>> wrote:<br>
>><br>
>> Dear all,<br>
>><br>
>> I just moved to Boston yesterday. 5yr assignment.<br>
>> Thanks<br>
>><br>
>> --<br>
>> Masataro Asai Ph.D<br>
>><br>
>> Research Staff Member<br>
>> IBM Research<br>
>><br>
>> Tel: +81-44-856-9009<br>
>> Mobile: +81-50-5534-1357<br>
>> Mail: <a href="mailto:guicho2.71828@gmail.com" target="_blank">guicho2.71828@gmail.com</a><br>
>> Website: <a href="http://guicho271828.github.io/" rel="noreferrer" target="_blank">http://guicho271828.github.io/</a><br>
>><br>
<br>
-- <br>
Masataro Asai Ph.D<br>
<br>
Research Staff Member<br>
IBM Research<br>
<br>
Tel: +81-44-856-9009<br>
Mobile: +81-50-5534-1357<br>
Mail: <a href="mailto:guicho2.71828@gmail.com" target="_blank">guicho2.71828@gmail.com</a><br>
Website: <a href="http://guicho271828.github.io/" rel="noreferrer" target="_blank">http://guicho271828.github.io/</a><br>
<br>
</blockquote></div>