✦ LIBER ✦

Neural networks as content addressable memories and learning machines

✍ Scribed by Roland Köberle

Publisher: Elsevier Science
Year: 1989
Tongue: English
Weight: 553 KB
Volume: 56
Category: Article
ISSN: 0010-4655
DOI: 10.1016/0010-4655(89)90051-9

No coin nor oath required. For personal study only.

✦ Synopsis

Some apects of content addressable memories implemented by neural networks are discussed, such as storage capacity, non-orthogonal memories, transparency to the outside world, non-equilibrium states, smooth forgetting, etc. As opposed to the usual yon Neumann computers, neural nets are not programmed, but trained. We describe and discuss two of the most popular mechanisms for implementing the training of neural nets, so that they may perform specific tasks: back-propagation and the Boltzmarm machine.

📜 SIMILAR VOLUMES

Making Machines Mimic Human and/or Anima

Making Machines Mimic Human and/or Animal Intelligence. Review of Artificial Neural Networks: Approximation & Learning Theory, by Halbert White with A. R. Gallant, K. Hornick, M. Stinchcombe, and J. Wooldridge

✍ Ramalingan Shanmugam 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 80 KB

Artificial Neural Networks Associated to

Artificial Neural Networks Associated to Calorimetric Measurements Used as a Method to Predict Polymer Composition of High Solid Content Emulsion Copolymerizations

✍ Domingos Sávio Giordani; Liliane M. F. Lona; Timothy F. McKenna; Maria A. Krähen 📂 Article 📅 2005 🏛 John Wiley and Sons 🌐 English ⚖ 223 KB

## Abstract **Summary:** Inspired by biological systems, artificial neural networks (ANN) have demonstrated to be powerful tools to model non‐linear systems, such as high solid content latexes produced by emulsion polymerization which have a great importance in the polymeric industry, essentially f