Spiking Neural Network Ink Drop Spread, Spike-IDS

Abstract

ALM is an adaptive recursive fuzzy learning algorithm which is inspired by some behavioral features of human brain functionality. This algorithm is fairly compatible with reductionism concept in philosophy of mind in which a complex system is representing as combination of partial simpler knowledge or superposition of sub-causes effects. This algorithm utilizes a fuzzy knowledge extraction engine which is called Ink Drop Spread in brief IDS. IDS is inspired by non-exact operation paradigm in brain, whether in hardware level or inference layer. It enables fine grained tunable knowledge extraction mechanism from information which is captured by sensory level of ALM. In this article we propose a spiking neural model for ALM where the partial knowledge that is extracted by IDS, can be captured and stored in the form of Hebbian type Spike-Time Dependent Synaptic Plasticity as is the case in the brain.