Variation and selection: An evolutionary model of learning in neural networks

✍ Scribed by Aviv Bergman

• Publisher: Elsevier Science
• Year: 1988
• Tongue: English
• Weight: 53 KB
• Volume: 1
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/0893-6080(88)90114-1

✦ Synopsis

The diversity of the living world has been shaped, it is believed, by Darwinian selection acting on random mutations. This paper deal with the same problem that evolution had to solve --how to form categories in a bottom-up manner from information in the environment, without incorporating the assumption of any particular observer. In the present work, we study the emergence of nontrivial computational capabilities in networks competing against each other in an environment where possession of such capabilities is an advantage.

Our approach is to simulate a variable population of network automata. In a way directly analogous to biological evolution, the population will converge, under the influence of selective pressure, to a group of automata that will be optimally suited for solving the task at hand. In addition to the standard neural network machinery, the important components of the approach are as follows: