Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

ICANN
2009
Springer

favoriteEmaildiscussreport

113views Neural Networks» more ICANN 2009»

Selective Attention Improves Learning

13 years 11 months ago

Selective Attention Improves Learning

Download www.lce.hut.fi

Abstract. We demonstrate that selective attention can improve learning. Considerably fewer samples are needed to learn a source separation problem when the inputs are pre-segmented by the proposed model. The model combines biased-competition model for attention with a habituation mechanism which allows the focus of attention to switch from one object to another. The criteria for segmenting objects are estimated from data and are shown to generalise to new objects. Key words: Selective attention, perceptual learning, segmentation

Antti Yli-Krekola, Jaakko Särelä, Harri

Real-time Traffic

Artificial Intelligence | ICANN 2009 | Model Combines Biased-competition | Selective Attention | Source Separation Problem |

claim paper

Related Content

» May We Have Your Attention Analysis of a Selective Attention Task

» Representations for Action Selection Learning from RealTime Observation of Task Experts

» A reinforcement learning model of selective visual attention

» Using Reinforcement Learning to Improve Exploration Trajectories for Error Minimization

» Selecting What Is Important Training Visual Attention

» Spatial selection for attentional visual tracking

» Visual Selection and Attention Shifting Based on FitzHughNagumo Equations

» Learning of PositionInvariant Object Representation Across Attention Shifts

» Preattentive Reading and Selective Attention for Document Image Analysis

Post Info
More Details (n/a)

Added	26 May 2010
Updated	26 May 2010
Type	Conference
Year	2009
Where	ICANN
Authors	Antti Yli-Krekola, Jaakko Särelä, Harri Valpola

Comments (0)