Evolution of Neural Modules

Evolution of Neural Modules Terry Bossomaier
Abstract
	Many artificial neural networks consist of layered populations of homogeneous cells, whereas biological networks have a highly modular structure. Clearly, some of this modular structure is derived genetically, but precise details are as yet unresolved. In this paper, we approach the problem from a computational viewpoint and consider how algorithmic information theory may serve as an alternative metric to communication theory for higher level visual tasks.

Full Text

Multimedia Links
(none)

Reference Links
(none)

Citation Reference

Get viewers
for PS & PDF

[CI Editor] [Site Manager]