No mystery intended

✍ Scribed by Stephen L. Thaler

• Book ID: 104348924
• Publisher: Elsevier Science
• Year: 1999
• Tongue: English
• Weight: 21 KB
• Volume: 12
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/s0893-6080(98)00111-7

✦ Synopsis

Editor: My 1995 Neural Networks article, '''Virtual input' phenomena within the death of a simple pattern associator'' addresses a heretofore unexplored connectionist topic: how any trained artificial neural network (ANN) tends to interpret its own internal damage as stored memories. The effect is investigated within a simple exemplary net and then generalized to a wide variety of ANN architectures and biological networks. The 'simpler' explanation of the virtual input phenomenon, which was later offered by Leow and Setiono, serves only as an alternative analysis of how this effect is realized within one narrow instance.