Using Song and Abott's (2000) code to enable synapses to learn the features of data

[kernfel]

A recent, relevant comment on using STDP for machine learning:

My attempt at implementing STDP on iris dataset

Again, I’m not a machine learner, but I feel that there is a misunderstanding about the role of STDP. It is not a learning rule in the sense that back propagation is, i.e. just presenting some stimuli and using STDP for the connections to a target neuron will not make these connections learn the stimulus class. If you present several different stimuli and simply add more output neurons and connections, you will end up with several output neurons that do the same thing, since they get exactly the…