Neuroscienceneural information processing systemsPeer-reviewed
Structured flexibility in recurrent neural networks via neuromodulation
Julia C. Costacurta, Shaunak Bhandarkar, David M. Zoltowski, Scott W. Linderman
This paper introduces a neuromodulated RNN model that uses synaptic gain scaling to improve training and generalization on canonical tasks, and shows how it implements gating mechanisms found in artificial RNNs.