ML Anthology

Learning in the Recurrent Random Neural Network

Erol Gelenbe
NeCo 1993 pp. 154-164
doi:10.1162/NECO.1993.5.1.154 /neco/1993/gelenbe1993neco-learning/

Abstract

The capacity to learn from examples is one of the most desirable features of neural network models. We present a learning algorithm for the recurrent random network model (Gelenbe 1989, 1990) using gradient descent of a quadratic error function. The analytical properties of the model lead to a "backpropagation" type algorithm that requires the solution of a system of n linear and n nonlinear equations each time the n-neuron network "learns" a new input-output pair.

NeCo Semantic Scholar

Cite

Text

Gelenbe. "Learning in the Recurrent Random Neural Network." Neural Computation, 1993. doi:10.1162/NECO.1993.5.1.154

Markdown

[Gelenbe. "Learning in the Recurrent Random Neural Network." Neural Computation, 1993.](https://mlanthology.org/neco/1993/gelenbe1993neco-learning/) doi:10.1162/NECO.1993.5.1.154

BibTeX

@article{gelenbe1993neco-learning,
  title     = {{Learning in the Recurrent Random Neural Network}},
  author    = {Gelenbe, Erol},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {154-164},
  doi       = {10.1162/NECO.1993.5.1.154},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/gelenbe1993neco-learning/}
}