NASA NTRS · 19900029219
The least constraint principle for learning in neurodynamics
Abstract
An adaptive neural network for auto-associative memories operating in continuous time is considered. A new learning algorithm for the weight matrix defined by explicit locations of desirable equilibrium points is introduced. The approach is based upon the minimum 'strength energy' of the weight matrix for each prescribed performance of the neural network.
Keep this discovery
Explore connections, maps & timelines
Zak, Michail. 1989-02-06. The least constraint principle for learning in neurodynamics. https://ntrs.nasa.gov/citations/19900029219
Cite the original work for its findings. Save a collection to share your selection of sources.