Machine Learning Classification Informed by a Functional Biophysical System

We present a novel machine learning architecture for classification suggested by experiments on the insect olfactory system. The network separates odors via a winnerless competition network, then classifies objects by projection into a high dimensional space where a support vector machine provides more precision in classification. We build this network using biophysical models of neurons with our results showing high discrimination among inputs and exceptional robustness to noise. The same circuitry accurately identifies the amplitudes of mixtures of the odors on which it has been trained.