Anhinga anhinga

A year ago I posted about dataflow programming and linear models of computation:

http://anhinga-anhinga.livejournal.com/82757.html

It turns out that those dataflow matrix machines are a fairly powerful generalization of recurrent neural networks.( Read more... )

This is a prototype of an elderly home care robot developed by a very small group at IBM (with the benign indifference from their employer corporation that does not want to deal with robots and headaches and liabilities associated with robots). Its ability to verbally communicate with a human and to learn from a human is very impressive (basically, one can program this robot to a large extent simply by talking to it). Here is a demo video from the talk at the AGI-12 conference:

http://www.youtube.com/watch?v=M2RXDI3QYNU

The paper itself, "An Extensible Language Interface for Robot Manipulation", explaining to some extent how this works can be found here:

http://www.mindmakers.org/boards/18/topics/73

and the free online version of AGI-12 proceedings is here (scroll down to AGI-12 Contributed Paper Sessions):

http://www.mindmakers.org/projects/agiconf-2012/wiki/Schedule

http://www.youtube.com/watch?v=ivst5hK6XqI

Winamp MilkDrop2 exercise; November 2011; HD resolution settings available

Informal meeting, Friday, June 1:

https://lists.ccs.neu.edu/pipermail/pl-seminar/2007/000390.html

Numenta is founded by Jeff Hawkins, the author of "On Intelligence" (memory-prediction framework).

A research release of their "Numenta Platform for Intelligent Computing" is now available for Linux and Mac OS (free, targeted at sophisticated developers for the purpose of education and experimentation, no deployment rights).

Some interesting paper titles on the page of Calculemus'06 (13th Symposium on the Integration of Symbolic Computation and Mechanized Reasoning 2006).

One of the authors, Simon Colton, wrote a thesis "Automated Theory Formation in Pure Mathematics", and one can read its table of contents on the Amazon site.

Found an event-driven simulation package for modeling large networks of spiking neurons (GNU public license), have not tried it yet:
http://www.sccn.ucsd.edu/~arno/spikenet/papers.html
http://www.sccn.ucsd.edu/~arno/spikenet

Browsed the proceedings of "Advances in natural computation : first international conference, ICNC 2005, Changsha, China, August 27-29, 2005 : proceedings / Lipo Wang, Ke Chen, Yew Soon Ong (eds.)." 3 very think volume of Lecture Notes in Computer Science, 3610-3612 at a nearby library. Almost 4000 pages of papers mostly by Chinese authors. At least they still chose to write in English... (DBLP link: http://www.informatik.uni-trier.de/~ley/db/conf/icnc)

Embedding programs into neural nets.

( details )

The Eighth Annual ICFP Programming Contest

Jun 24-27, Jul 9-10.

"This year's competition rewards programmers who can plan ahead. As before, we'll announce a problem and give you three days to solve it. Two weeks later, we'll announce a change to the problem specification and give you one day to adapt your program to the new spec. And you guessed it: the second half will be worth considerably more than the first."

A quite decent automatic CS paper generator. The generated papers even have a decent chance of being accepted at "junk conferences".

Hat tip: mathemajician and aa_kir

UPDATE: made CNN.