Analysis of oscillatory weight changes from online learning with filtered spiking feedback

Tech Report, 2017

Aaron R. Voelker, Chris Eliasmith

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 spiking neurons to minimize an error signal. Continuing the work of Voelker (2015), we solve for the dynamics of PES, while filtering the error with an arbitrary linear synapse model. For the most common case of a lowpass filter, the continuous-time weight changes are characterized by a second-order bandpass filter with frequency $\omega = \sqrt {\tau ^{-1} \kappa \|{\bf a}\|^2 }$ and bandwidth $Q = \sqrt {\tau \kappa \|{\bf a}\|^2 }$, where τ is the exponential time constant, κ is the learning rate, and ${\bf a}$ is the activity vector. Therefore, the error converges to zero, yet oscillates if and only if $\tau \kappa \|{\bf a}\|^2 > \frac {1}{4}$. This provides a heuristic for setting κ based on the synaptic τ, and a method for engineering remarkably accurate decaying oscillators using only a single spiking leaky integrate-and-fire neuron.

Full text links

External link

CTN Tech Report

Issn
CTN-TR-20171001-013
Address
Waterloo, ON
Month
10
Doi
10.13140/RG.2.2.15438.77128
Institution
Centre for Theoretical Neuroscience

Cite

Plain text

BibTeX