Some Effects of Individual Learning on the Evolution of Sensors

Jung, Tobias; Dauscher, Peter; Uthmann, Thomas

doi:10.1007/3-540-44811-x_47

Cited by 3 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was found that the cortical cells selective for orientation in the kittens preferred to fire mostly in response to the orientation that they had been exposed to. Evolution of sensory layout in an artificial agent was considered in (Jung et al, 2001) in relation to learning, where it was shown that longer learning periods lead to better suited sensors. In this paper we also consider the selective pressure posed by the trade-off between redundancy and novelty in sensoric input.…”

Section: Introductionmentioning

confidence: 99%

Information Trade-Offs and the Evolution of Sensory Layouts

Pollack¹,

Husbands²,

Watson³

et al. 2004

Artificial Life IX

View full text Add to dashboard Cite

In nature, sensors evolve to capture relevant information needed for organisms of a particular species to survive and reproduce. In this paper we study how sensor layouts may evolve in different environments and under pressure of different informational constraints. To do this we evolve sensor layouts for different environments and constraints using a fitness measure with weighted terms for redundancy and novelty, using, respectively, mutual information and Crutchfield's information metric. The results show how different sensor layouts evolve depending on the structure and complexity of the environment but also how selective pressure for redundancy or novelty might affect the design.

show abstract

Section: Introductionmentioning

confidence: 99%