A Solution to the Dynamics of the Prescribed Error Sensitivity Learning Rule

Tech Report, 2015

Aaron R. Voelker

Abstract

Prescribed Error Sensitivity (PES) is a biologically plausible supervised learning rule that is frequently used with the Neural Engineering Framework (NEF). PES modifies the connection weights between populations of neurons to minimize an external error signal. We solve the discrete dynamical system for the case of constant inputs and no noise, to show that the decoding vectors given by the NEF have a simple closed-form expression in terms of the number of simulation timesteps. Moreover, with $\gamma = (1 - \kappa ||a||^2) < 1$, where κ is the learning rate and a is the vector of firing rates, the error at timestep $k$ is the initial error times $\gamma ^k$. Thus, $\gamma > -1$ implies exponential convergence to a unique stable solution, $\gamma < 0$ results in oscillatory weight changes, and $\gamma \le -1$ implies instability.

Full text links

PDF

External link

CTN Tech Report

Issn
CTN-TR-20151001-01
Address
Waterloo, ON
Month
10
Doi
10.13140/RG.2.1.3048.0084
Institution
Centre for Theoretical Neuroscience

Cite

Plain text

BibTeX