2 papers
cs.LG2026
Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning
Ruiwu Niu, Xiaowen Bi, Michaël Antonie van Wyk
Physical learning lets a trainable material or network use its own physical response to carry error signals, reducing the need for a separately programmed backward computation. We…
eess.SY2020
Multivaluedness in Networks: Theory
Michael Antonie van Wyk
An unexpected and somewhat surprising observation is that two counter-cascaded systems, given the right conditions, can exhibit multivaluedness from one of the outputs to the other…