Paper Info
Title
Discretized ISO-learning neural network for obstacle avoidance in reactive robot controllers
Abstract
Isotropic sequence order learning (ISO-learning) and its variations, input correlation only learning (ICO-learning) and ISO three-factor learning (ISO3-learning) are unsupervised neural algorithms to learn temporal differences. As robotic software operates mainly in discrete time domain, a discretization of ISO-learning is needed to apply classical conditioning to reactive robot controllers. Discretization of ISO-learning is achieved by modifications to original rules: weights sign restriction, to adequate ISO-learning devices outputs to the usually predefined kinds of connections (excitatory/inhibitory) used in neural networks, and decay term in learning rate for weights stabilization. Discrete ISO-learning devices are included into neural networks used to learn simple obstacle avoidance in the reactive control of two real robots.
Year
DOI
Venue
2009
10.1016/j.neucom.2008.06.019
Neurocomputing
Keywords
Field
DocType
discrete iso-learning device,neural algorithm,reactive control,neural network,discretized iso-learning neural network,isotropic sequence order learning,iso-learning,iso three-factor learning,adequate iso-learning devices output,weights sign restriction,reactive robot controller,obstacle avoidance,braitenberg's vehicles,classical conditioning,weights stabilization,temporal sequence learning,reactive robot control,temporal difference,robot control,sequence learning,discrete time
Obstacle avoidance,Discretization,Competitive learning,Computer science,Discrete time domain,Software,Artificial intelligence,Robot,Artificial neural network,Classical conditioning,Machine learning
Journal
Volume
Issue
ISSN
72
4-6
Neurocomputing
Citations 
PageRank 
References 
1
0.37
8
Authors
3
Name
Order
Citations
PageRank
José Manuel Cuadra Troncoso15310.58
José R. Álvarez Sánchez230.76
Félix de la Paz López3275.16