Discretization of ISO-Learning and ICO-Learning to Be Included into Reactive Neural Networks for a Robotics Simulator

Authors:
José M. Cuadra Troncoso;José R. Álvarez Sánchez;Félix Paz López
Affiliations:
Departamento de Inteligencia Artificial, UNED, Spain;Departamento de Inteligencia Artificial, UNED, Spain;Departamento de Inteligencia Artificial, UNED, Spain
Venue:
IWINAC '07 Proceedings of the 2nd international work-conference on Nature Inspired Problem-Solving Methods in Knowledge Engineering: Interplay Between Natural and Artificial Computation, Part II
Year:
2007

Citing 7
Cited 1

Signals & systems (2nd ed.)

Signals & systems (2nd ed.)
The Case for Graph-Structured Representations

ICCBR '97 Proceedings of the Second International Conference on Case-Based Reasoning Research and Development
Isotropic sequence order learning

Neural Computation
ISO learning approximates a solution to the inverse-controller problem in an unsupervised behavioral paradigm

Neural Computation
Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning

Neural Computation
Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only

Neural Computation
Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only

Neural Computation

Formal modeling of robot behavior with learning

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Isotropic Sequence Order learning (ISO-learning) and Input Correlation Only learning (ICO-learning) are unsupervised neural algorithms to learn temporal differences. The use of devices implementing this algorithms by simulation in reactive neural networks is proposed. We have applied several modifications to original rules: weights sign restriction, to adequate ISO-learning and ICO-learning devices outputs to the usually predefined kinds of connections (excitatory/inhibitory) used in neural networks, and decay term inclusion for weights stabilization. Original experiments with these algorithms are replicated as accurate as possible with a simulated robot and a discretization of the algorithms. Results are similar to those obtained in original experiments with analogue devices.