Supervised Learning in Spiking Neural Networks with FORCE Training

TL;DR

This paper demonstrates the application of FORCE training to spiking neural networks, enabling them to mimic complex dynamical systems, classify inputs, and reproduce behaviors inspired by biological neural circuits.

Contribution

It introduces the use of FORCE training in spiking neural networks to replicate complex behaviors and creates biologically motivated models of songbird singing and hippocampal replay.

Findings

FORCE-trained networks mimic complex behaviors

Reproduce songbird singing and hippocampal replay

Provide insights into neural dynamics and responses

Abstract

Populations of neurons display an extraordinary diversity in the behaviors they affect and display. Machine learning techniques have recently emerged that allow us to create networks of model neurons that display behaviours of similar complexity. Here, we demonstrate the direct applicability of one such technique, the FORCE method, to spiking neural networks. We train these networks to mimic dynamical systems, classify inputs, and store discrete sequences that correspond to the notes of a song. Finally, we use FORCE training to create two biologically motivated model circuits. One is inspired by the zebra-finch and successfully reproduces songbird singing. The second network is motivated by the hippocampus and is trained to store and replay a movie scene. FORCE trained networks reproduce behaviors comparable in complexity to their inspired circuits and yield information not easily obtainable with other techniques such as behavioral responses to pharmacological manipulations and spike timing statistics.