Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 15, NO. 3, MAY 2004 639 Cognitive Navigation Based on Nonuniform Gabor
 

Summary: IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 15, NO. 3, MAY 2004 639
Cognitive Navigation Based on Nonuniform Gabor
Space Sampling, Unsupervised Growing Networks,
and Reinforcement Learning
Angelo Arleo, Fabrizio Smeraldi, and Wulfram Gerstner
Abstract--We study spatial learning and navigation for au-
tonomous 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

  

Source: Arleo, Angelo - Laboratory of Neurobiology of Adaptive Processes, Université Pierre-et-Marie-Curie, Paris 6

 

Collections: Biology and Medicine