Machine Learning Classification Informed by a Functional Biophysical System

TL;DR

This paper introduces a novel machine learning architecture inspired by olfactory neural systems, combining biophysical models and SVMs for high-precision, noise-robust classification and mixture component analysis.

Contribution

It proposes a new neural network architecture that integrates winnerless competition with SVMs, inspired by biophysical olfactory systems, for improved classification and mixture analysis.

Findings

High discrimination accuracy among inputs

Robustness to noise demonstrated

Precise concentration determination of mixture components

Abstract

We present a novel machine learning architecture for classification suggested by experiments on olfactory systems. The network separates input stimuli, represented as spatially distinct currents, via winnerless competition---a process based on the intrinsic sequential dynamics of the neural system---then uses a support vector machine (SVM) to provide precision to the space-time separation of the output. The combined network uses biophysical models of neurons and shows high discrimination among inputs and robustness to noise. While using the SVM alone does not permit determination of the components of mixtures of classified inputs, the combined network is able to tell the precise concentrations of the constituent parts.