Neuronal architecture extracts statistical temporal patterns

TL;DR

This paper demonstrates that a biologically inspired feedforward neuronal model can extract and utilize higher-order temporal statistical information for time series classification, outperforming classical machine learning in parameter efficiency.

Contribution

The study introduces a simple neural model that leverages non-linear gain functions to transfer higher-order correlations into mean signals for improved classification.

Findings

Model extracts information up to third-order cumulants.

Biological architecture outperforms classical schemes in parameter efficiency.

Effective on both synthetic and real-world datasets.

Abstract

Neuronal systems need to process temporal signals. We here show how higher-order temporal (co-)fluctuations can be employed to represent and process information. Concretely, we demonstrate that a simple biologically inspired feedforward neuronal model is able to extract information from up to the third order cumulant to perform time series classification. This model relies on a weighted linear summation of synaptic inputs followed by a nonlinear gain function. Training both - the synaptic weights and the nonlinear gain function - exposes how the non-linearity allows for the transfer of higher order correlations to the mean, which in turn enables the synergistic use of information encoded in multiple cumulants to maximize the classification accuracy. The approach is demonstrated both on a synthetic and on real world datasets of multivariate time series. Moreover, we show that the biologically inspired architecture makes better use of the number of trainable parameters as compared to a classical machine-learning scheme. Our findings emphasize the benefit of biological neuronal architectures, paired with dedicated learning algorithms, for the processing of information embedded in higher-order statistical cumulants of temporal (co-)fluctuations.