Skip to main content
Open Access Publications from the University of California

UC Berkeley

UC Berkeley Previously Published Works bannerUC Berkeley

Computing with Dynamic Attractors in Neural Networks


Recurrent neural network models with parallel distributed architecture are constructed using ordinary differential equations. Models of associative memory are constructed using chaotic attractors. The learned memories are represented by arbitrary attractors, which can be oscillatory or chaotic.

Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View