Machine Learning Classification Informed by a Functional Biophysical System
This work addresses classification challenges in domains like sensory processing or chemical analysis by offering a biologically inspired method, though it appears incremental as it combines existing biophysical models with SVM.
The authors tackled the problem of classifying mixtures of inputs by developing a machine learning architecture inspired by olfactory systems, which uses winnerless competition and an SVM to achieve high discrimination and robustness to noise, enabling precise determination of constituent concentrations where SVM alone fails.
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.