Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks
Two closed-loop forecasting strategies, in which the network's own generated values are fed back into the network as if they were observed past values, are explored, which perform comparably to or better than zero-masking with S4, and in most cases match SpaceTime.
Erik Stolt, Sanja Karilanova, Ayça Özçelikkale
· 0 citations