News for hackers. Stuff that matters.
Re:Study reveals how, when a synapse strengthens, its neighb... by nabla9 on Sunday June 24, 2018 @03:12PM (#17387901)
In deep learning this is called local response normalization (LRN).

ConvNets use LRN where most active neurons inhibit other neurons at the same location in neighboring feature maps. http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf

Re:Study reveals how, when a synapse strengthens, its neighb... by adityab on Sunday June 24, 2018 @04:32PM (#17388257)
Actually the new finding is similar to weight normalisation for individual neurons. LRN would be similar to another thing called lateral inhibition.