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

Authors:
Bernd Porr;Christian von Ferber;Florentin Wörgötter
Affiliations:
Department of Psychology, University of Stirling, Stirling FK9 4LA, Scotland;Theoretical Polymer Physics, Freiburg University, 79104 Freiburg, Germany;Department of Psychology, University of Stirling, Stirling FK9 4LA, Scotland
Venue:
Neural Computation
Year:
2003

Citing 7
Cited 8

Filtering in the time and frequency domains

Filtering in the time and frequency domains
Control systems engineering

Control systems engineering
Android epistemology

Android epistemology
A bottom up approach towards the acquisition and expression of sequential representions applied to a behaving real-world device: Distributed Adaptive Control III

Neural Networks - Special issue on neural control and robotics: biology and technology
Discrete Random Signals and Statistical Signal Processing

Discrete Random Signals and Statistical Signal Processing
Linear Control System Analysis and Design: Conventional and Modern

Linear Control System Analysis and Design: Conventional and Modern
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation

Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

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
Learning with “Relevance”: Using a Third Factor to Stabilize Hebbian Learning

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

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
Discretized ISO-learning neural network for obstacle avoidance in reactive robot controllers

Neurocomputing
A neural model for the adaptive control of saccadic eye movements

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Unifying perceptual and behavioral learning with a correlative subspace learning rule

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In "Isotropic Sequence Order Learning" (pp. 831-864 in this issue), we introduced a novel algorithm for temporal sequence learning (ISO learning). Here, we embed this algorithm into a formal nonevaluating (teacher free) environment, which establishes a sensor-motor feedback. The system is initially guided by a fixed reflex reaction, which has the objective disadvantage that it can react only after a disturbance has occurred. ISO learning eliminates this disadvantage by replacing the reflex-loop reactions with earlier anticipatory actions. In this article, we analytically demonstrate that this process can be understood in terms of control theory, showing that the system learns the inverse controller of its own reflex. Thereby, this system is able to learn a simple form of feedforward motor control.