no code implementations • 23 Jun 2020 • Laureline Logiaco, G. Sean Escola
Given a known set of motifs, can a new motif be learned without affecting the performance of the known set and then used in new sequences without first explicitly learning every possible transition?
1 code implementation • 9 Oct 2017 • Brian DePasquale, Christopher J. Cueva, Kanaka Rajan, G. Sean Escola, L. F. Abbott
We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations.