1Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Canada.
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Deterministic Boltzmann machines show unstable learning for nonlinear problems due to over-parameterization. This research introduces reliability as a new metric to measure network robustness against weight drift and output errors.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: