reinforcement learning with spikes; jaguar cubs

[anhinga_anhinga]

More 10th ICCNS findings: Razvan Florian (Romania) presented a poster, "Reinforcement learning for spiking neural networks with modulated spike-timing-dependent plasticity". Basically, this modifies the reinforcement learning approach by Jonathan Baxter and Peter Bartlett for the situation with spikes. (One nice thing is that training for XOR works successfully in this case. I had difficulties with making the classical Baxter-Bartlett setup to work for XOR, either because of some principal problems, or because my hands grow from the wrong places.) His papers are here:

http://www.coneural.org/florian/

Meanwhile, Bostonians can see jaguar cubs at Stone Zoo in Stoneham. Here are some photos:

http://www.boston.com/news/local/massachusetts/gallery/052506_stonehamzoo_jaguars/

Comments

[dklein.livejournal.com]

I think a study of using spikes for reinforcement of
writing a paper and not looking at livejournal every
now and then is long overdue.

[anhinga-anhinga.livejournal.com]

Might this be a case of XOR? ;-)

Certainly, equipping livejournal pages with electroshock output, and a LaTeX-oriented text editor with a pomegranate juice dispenser would go a long way towards learning the desired goal ;-)