Sciweavers

Share
NIPS
1993

Structural and Behavioral Evolution of Recurrent Networks

8 years 9 months ago
Structural and Behavioral Evolution of Recurrent Networks
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algorithms, GNARL employs a population of networks and uses a fitness function’s unsupervised feedback to guide search through network space. Annealing is used in generating both gaussian weight changes and structural modifications. Applying GNARL to a complex search and collection task demonstrates that the system is capable of inducing networks with complex internal dynamics.
Gregory M. Saunders, Peter J. Angeline, Jordan B.
Added 02 Nov 2010
Updated 02 Nov 2010
Type Conference
Year 1993
Where NIPS
Authors Gregory M. Saunders, Peter J. Angeline, Jordan B. Pollack
Comments (0)
books