A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons

This paper presents a hybrid learning algorithmfor spiking neural networks (SNNs), referred to as an evolvablespiking neural network (ESNN) paradigm. The algorithmintegrates a supervised and unsupervised learning approach.The unsupervised approach exploits a Spike Timing DependentPlasticity (STDP) mechanism with explicit delay learningfor multiple connections between neurons. Supervision of thesynaptic delays and the excitatory/inhibitory connections isgoverned by a genetic algorithm (GA), while the STDP rule isfree to operate in its normal unsupervised manner. A spike trainencoding/decoding scheme is developed for the algorithm. Theapproach is validated by application to the Iris classificationproblem.