Support vector machines for spike pattern classification with a leaky integrate-and-fire neuron

Abstract

Read online

Spike pattern classification is a key topic in machine learning, computational neuroscience and electronic device design. Here we offer a new approach for supervised spike pattern classification, combining a bio-mimetic neuron model with a method based on Support Vector Machines. We compare classification performance between this algorithm and other methods sharing the same conceptual framework. We consider the effect of postsynaptic potential kernel dynamics on patterns separability, and we propose an extension of the method to decrease computational load. The algorithm performs well in generalization tasks. We show that the peak value of spike patterns separability depends on a relation between postsynaptic potential dynamics and spike pattern duration, and we propose a particular kernel that is well-suited for fast computations and electronic implementations.

Keywords

• machine learning
• supervised learning rule
• synaptic kernel
• Tempotron
• linear separation