/* ---- Google Analytics Code Below */

Monday, March 14, 2016

New Learning Methods for Neural Networks

We used mostly error back propagation.  How will this influence new methods being used for classification?  Technical, worth a deeper look in the linked paper.  Possible link to IOT sensory applications?

In CACM:  " ... The model is based on a synaptic learning rule in which individual neurons can increase or decrease their activity in response to a simple learning signal.

Gutig says he has employed this rule to establish an "'aggregate-label' learning procedure...built on the concept of setting the connections between cells in such a way that the resulting neural activity over a certain period is proportional to the number of cues."

Gutig's model also performs well when there is a delay between the cue and the event or outcome, by interpreting the average neural activity within a network as a learning signal. He says this "self-supervised" learning conforms to a principle differing from the Hebbian theory often applied in artificial neural networks.  ... " 

No comments: