Hardware-Amenable Structural Learning for Spike-based Pattern Classification using a Simple Model of Active Dendrites

TL;DR

This paper introduces a hardware-friendly spike-based neuron model with dendritic compartments and a simple structural plasticity learning rule, enabling efficient high-dimensional binary pattern classification with reduced computational resources.

Contribution

It proposes a novel, hardware-amenable dendritic neuron model with a simple, biologically inspired learning algorithm for efficient pattern classification.

Findings

Achieves comparable accuracy to SVM and ELM on benchmark tasks.

Uses 10-50% fewer computational resources.

Supports integration into neuromorphic systems.

Abstract

This paper presents a spike-based model which employs neurons with functionally distinct dendritic compartments for classifying high dimensional binary patterns. The synaptic inputs arriving on each dendritic subunit are nonlinearly processed before being linearly integrated at the soma, giving the neuron a capacity to perform a large number of input-output mappings. The model utilizes sparse synaptic connectivity; where each synapse takes a binary value. The optimal connection pattern of a neuron is learned by using a simple hardware-friendly, margin enhancing learning algorithm inspired by the mechanism of structural plasticity in biological neurons. The learning algorithm groups correlated synaptic inputs on the same dendritic branch. Since the learning results in modified connection patterns, it can be incorporated into current event-based neuromorphic systems with little overhead. This work also presents a branch-specific spike-based version of this structural plasticity rule. The proposed model is evaluated on benchmark binary classification problems and its performance is compared against that achieved using Support Vector Machine (SVM) and Extreme Learning Machine (ELM) techniques. Our proposed method attains comparable performance while utilizing 10 to 50% less computational resources than the other reported techniques.