Linked Life Data

15384552

Source:http://linkedlifedata.com/resource/pubmed/id/15384552

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
3
pubmed:dateCreated
2004-9-23
pubmed:abstractText
We study spatial learning and navigation for autonomous agents. A state space representation is constructed by unsupervised Hebbian learning during exploration. As a result of learning, a representation of the continuous two-dimensional (2-D) manifold in the high-dimensional input space is found. The representation consists of a population of localized overlapping place fields covering the 2-D space densely and uniformly. This space coding is comparable to the representation provided by hippocampal place cells in rats. Place fields are learned by extracting spatio-temporal properties of the environment from sensory inputs. The visual scene is modeled using the responses of modified Gabor filters placed at the nodes of a sparse Log-polar graph. Visual sensory aliasing is eliminated by taking into account self-motion signals via path integration. This solves the hidden state problem and provides a suitable representation for applying reinforcement learning in continuous space for action selection. A temporal-difference prediction scheme is used to learn sensorimotor mappings to perform goal-oriented navigation. Population vector coding is employed to interpret ensemble neural activity. The model is validated on a mobile Khepera miniature robot.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
May
pubmed:issn
1045-9227
pubmed:author
pubmed:issnType
Print
pubmed:volume
15
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
639-52
pubmed:dateRevised
2006-11-15
pubmed:meshHeading
pubmed:year
2004
pubmed:articleTitle
Cognitive navigation based on nonuniform Gabor space sampling, unsupervised growing networks, and reinforcement learning.
pubmed:affiliation
Neuroscience Group, SONY Computer Science Laboratory, 75005 Paris, France. angelo.arleo@csi.sony.fr
pubmed:publicationType
Journal Article, Research Support, Non-U.S. Gov't