CoLaNET -- A Spiking Neural Network with Columnar Layered Architecture for Classification

TL;DR

This paper introduces CoLaNET, a novel spiking neural network with a columnar layered architecture designed for classification tasks, combining prototypical structures, local plasticity rules, and suitability for neurochip implementation.

Contribution

It presents a new SNN architecture with columnar layers and a unique plasticity mechanism, advancing hardware-friendly neural network designs for classification.

Findings

High performance on a model-based reinforcement learning task

Effective classification with biologically plausible plasticity rules

Architecture suitable for implementation on neurochips

Abstract

In the present paper, I describe a spiking neural network (SNN) architecture which, can be used in wide range of supervised learning classification tasks. It is assumed, that all participating signals (the classified object description, correct class label and SNN decision) have spiking nature. The distinctive feature of this architecture is a combination of prototypical network structures corresponding to different classes and significantly distinctive instances of one class (=columns) and functionally differing populations of neurons inside columns (=layers). The other distinctive feature is a novel combination of anti-Hebbian and dopamine-modulated plasticity. The plasticity rules are local and do not use the backpropagation principle. Besides that, as in my previous studies, I was guided by the requirement that the all neuron/plasticity models should be easily implemented on modern neurochips. I illustrate the high performance of my network on a task related to model-based reinforcement learning, namely, evaluation of proximity of an external world state to the target state.