Energy Constraints Improve Liquid State Machine Performance
This work addresses performance enhancement for seizure detection systems, but it appears incremental as it builds on existing liquid state machine methods with specific constraints.
The researchers tackled the problem of improving liquid state machine performance by applying metabolic energy constraints, resulting in a 4.25% increase in testing accuracy on a seizure detection task and a 6.9% reduction in reservoir spiking activity.
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% was observed on a seizure detection task using a digital liquid state machine while reducing overall reservoir spiking activity by 6.9%. The accuracy improvements appear to be linked to the energy constraints' impact on the reservoir's dynamics, as measured through metrics such as the Lyapunov exponent and the separation of the reservoir.