Book
Open access
Jul 2026
EvoPlaSNN: Evolving Reward-modulated ANN-based Plasticity Rule for Spiking Neural Networks
It is found that using synaptic weight as inputs has no effect on rule performance, while utilising either pre-before-post or post-before-pre eligibility trace is better than a trace that combines both.
Napat Sahapat, S. Chevtchenko, Y. Bethi et al.
· GECCO Companion · 0 citations