Skip to main content
Advertisement

< Back to Article

Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates

Fig 2

FORCE training spiking LIF and LIF-matched rate networks.

The single layer recurrent neural network used in the FORCE method consists of: a set of fixed reservoir weights, a set of fixed encoder weights and a set of learned decoder weights. The reservoir network creates a chaotic pool of rich mixed dynamics which are used to linearly decode the target supervisor with . This decoder (S for spikes, R for rates) is learned online using the Recursive Least Squares (RLS) algorithm. The encoder weights then feedback the decoded output into the reservoir to stabilize the dynamics.

Fig 2

doi: https://doi.org/10.1371/journal.pcbi.1013224.g002