HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Porr, B. Articles by Wörgötter, F. Search for Related Content PubMed PubMed Citation Articles by Porr, B. Articles by Wörgötter, F.

Isotropic Sequence Order Learning

bp1{at}cn.stir.ac.uk, Department of Psychology, University of Stirling, Stirling FK9 4LA, Scotland

Florentin Wörgötter

worgott{at}cn.stir.ac.uk, Department of Psychology, University of Stirling, Stirling FK9 4LA, Scotland

In this article, we present an isotropic unsupervised algorithm for temporal sequence learning. No special reward signal is used such that all inputs are completely isotropic. All input signals are bandpass filtered before converging onto a linear output neuron. All synaptic weights change according to the correlation of bandpass-filtered inputs with the derivative of the output. We investigate the algorithm in an open- and a closed-loop condition, the latter being defined by embedding the learning system into a behavioral feedback loop. In the open-loop condition, we find that the linear structure of the algorithm allows analytically calculating the shape of the weight change, which is strictly heterosynaptic and follows the shape of the weight change curves found in spike-time-dependent plasticity. Furthermore, we show that synaptic weights stabilize automatically when no more temporal differences exist between the inputs without additional normalizing measures. In the second part of this study, the algorithm is is placed in an environment that leads to closed sensor-motor loop. To this end, a robot is programmed with a prewired retraction reflex reaction in response to collisions. Through isotropic sequence order (ISO) learning, the robot achieves collision avoidance by learning the correlation between his early range-finder signals and the later occurring collision signal. Synaptic weights stabilize at the end of learning as theoretically predicted. Finally, we discuss the relation of ISO learning with other drive reinforcement models and with the commonly used temporal difference learning algorithm. This study is followed up by a mathematical analysis of the closed-loop situation in the companion article in this issue, "ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm" (pp. 865–884).

This article has been cited by other articles:

				B. Porr and F. Worgotter Learning with "Relevance": Using a Third Factor to Stabilize Hebbian Learning Neural Comput., October 1, 2007; 19(10): 2694 - 2719. [Abstract] [Full Text] [PDF]

				S. M. Bohte and M. C. Mozer Reducing the variability of neural responses: a computational theory of spike-timing-dependent plasticity. Neural Comput., February 1, 2007; 19(2): 371 - 403. [Abstract] [Full Text] [PDF]

				B. Porr and F. Worgotter Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only. Neural Comput., June 1, 2006; 18(6): 1380 - 1412. [Abstract] [Full Text] [PDF]

				T. Geng, B. Porr, and F. Worgotter A reflexive neural network for dynamic biped walking control. Neural Comput., May 1, 2006; 18(5): 1156 - 1196. [Abstract] [Full Text] [PDF]

				F. Worgotter and B. Porr Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms Neural Comput., February 1, 2005; 17(2): 245 - 319. [Abstract] [Full Text] [PDF]

				A. Saudargiene, B. Porr, and F. Worgotter How the Shape of Pre- and Postsynaptic Signals Can Influence STDP: A Biophysical Model Neural Comput., March 1, 2004; 16(3): 595 - 625. [Abstract] [Full Text] [PDF]