Energy Constraints Improve Liquid State Machine Performance

06/08/2020

∙

by   Andrew Fountain, et al.

∙

0

∙

share

A model of metabolic energy constraints is applied to a liquid state machine in order to analyze its effects on network performance. It was found that, in certain combinations of energy constraints, a significant increase in testing accuracy emerged; an improvement of 4.25 task using a digital liquid state machine while reducing overall reservoir spiking activity by 6.9 energy constraints' impact on the reservoir's dynamics, as measured through metrics such as the Lyapunov exponent and the separation of the reservoir.