News for hackers. Stuff that matters.
Re:Yann LeCun on the IBM neural net chip by jimfleming on Saturday August 09, 2014 @06:28PM (#8158182)
Out of curiosity, does anyone know why they choose I&F instead of Izhikevich neurons[1] which model more biological spike forms. Perhaps to meet the low power consumption goals?

Also, how do convolutional neural networks model time? I thought that was one of the benefits of spiking networks and STDP.

1. http://www.izhikevich.org/publications/whichmod.pdf

Re:Yann LeCun on the IBM neural net chip by marmaduke on Saturday August 09, 2014 @06:46PM (#8158216)
The Izhikevich neuron is a two-dimensional system where I&F are usually one-dimensional, and the former has a larger number of parameters. Mathematical analysis (and implementation perhaps) is easier for the simpler I&F.