Unsupervised Learning of Spatio-Temporal Patterns in Spiking Neuronal Networks

TL;DR

This paper extends a biologically plausible spiking neural network model to unsupervisedly learn and predict diverse spatio-temporal patterns, improving its ability to handle complex sequences and demonstrating robustness across various input conditions.

Contribution

The work introduces plastic input synapses to a sequence learning model, enabling it to detect and learn a wider range of spatio-temporal patterns beyond synchronous spikes.

Findings

Model successfully learns and predicts high-order sequences.

Enhanced robustness across different input settings.

Capable of handling diverse spatio-temporal patterns.

Abstract

The ability to predict future events or patterns based on previous experience is crucial for many applications such as traffic control, weather forecasting, or supply chain management. While modern supervised Machine Learning approaches excel at such sequential tasks, they are computationally expensive and require large training data. A previous work presented a biologically plausible sequence learning model, developed through a bottom-up approach, consisting of a spiking neural network and unsupervised local learning rules. The model in its original formulation identifies only a specific type of sequence elements composed of synchronous spikes by activating a subset of neurons with identical stimulus preference. In this work, we extend the model to detect and learn sequences of various spatio-temporal patterns (STPs) by incorporating plastic connections in the input synapses. We showcase that the model is able to learn and predict high-order sequences. We further study the robustness of the model against different input settings and parameters.