The Principle of Weight Divergence Facilitation for Unsupervised Pattern Recognition in Spiking Neural Networks

Parallels between the signal processing tasks and biological neurons lead to an understanding of principles self-organized optimization input recognition. In present paper, we discuss such similarities among technical systems. We propose adding well-known STDP synaptic plasticity rule direct weight modification towards state associated with maximal difference background noise correlated signals. use principle physically constrained growth as a basis for weights’ control. It is proposed that existence production bio-chemical ‘substances’ needed development restrict straight modification. this information about noise-to-signal ratio controls substances’ storage drives neuron’s pressures best signal-to-noise ratio. consider several experiments different regimes understand functioning approach.