Neural circuits for dynamics-based segmentation of time series

TL;DR

This paper introduces two biologically plausible algorithms for segmenting time series based on underlying dynamics, capable of working in streaming settings with local learning rules, and demonstrates their effectiveness on autoregressive and voice data.

Contribution

The paper presents two novel algorithms for dynamic segmentation that are biologically plausible, one model-based with feedback and one model-free, suitable for streaming data.

Findings

Both algorithms achieve segmentation accuracy comparable to oracle methods.

Algorithms perform well on autoregressive models with piecewise-constant parameters.

Effective on real-world voice recording datasets.

Abstract

The brain must extract behaviorally relevant latent variables from the signals streamed by the sensory organs. Such latent variables are often encoded in the dynamics that generated the signal rather than in the specific realization of the waveform. Therefore, one problem faced by the brain is to segment time series based on underlying dynamics. We present two algorithms for performing this segmentation task that are biologically plausible, which we define as acting in a streaming setting and all learning rules being local. One algorithm is model-based and can be derived from an optimization problem involving a mixture of autoregressive processes. This algorithm relies on feedback in the form of a prediction error, and can also be used for forecasting future samples. In some brain regions, such as the retina, the feedback connections necessary to use the prediction error for learning are absent. For this case, we propose a second, model-free algorithm that uses a running estimate of the autocorrelation structure of the signal to perform the segmentation. We show that both algorithms do well when tasked with segmenting signals drawn from autoregressive models with piecewise-constant parameters. In particular, the segmentation accuracy is similar to that obtained from oracle-like methods in which the ground-truth parameters of the autoregressive models are known. We also test our methods on datasets generated by alternating snippets of voice recordings. We provide implementations of our algorithms at https://github.com/ttesileanu/bio-time-series.