title: May We Have Your Attention: Analysis of a Selective Attention Task
creator: Goldenberg, Eldan
creator: Garcowski, Jacob R
creator: Beer, Randall D
subject: Dynamical Systems
subject: Artificial Intelligence
description: In this paper we present a deeper analysis than has previously been carried out of a selective attention problem, and the evolution of continuous-time recurrent neural networks to solve it. We show that the task has a rich structure, and agents must solve a variety of subproblems to perform well. We consider the relationship between the complexity of an agent and the ease with which it can evolve behavior that generalizes well across subproblems, and demonstrate a shaping protocol that improves generalization.
publisher: MIT Press (Bradford Books)
contributor: Schaal, Stefan
contributor: Ijspeert, Auke
contributor: Billard, Aude
contributor: Vijayakumar, Sethu
contributor: Hallam, John
contributor: Meyer, Jean-Arcady
date: 2004
type: Conference Paper
type: PeerReviewed
format: application/pdf
identifier: http://cogprints.org/4950/1/GoldenbergGarcowskiSAB04.pdf
identifier:   Goldenberg, Eldan and Garcowski, Jacob R and Beer, Randall D  (2004) May We Have Your Attention: Analysis of a Selective Attention Task.  [Conference Paper]     
relation: http://cogprints.org/4950/