Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

April 1, 2003, Vol. 15, No. 4, Pages 865-884
(doi: 10.1162/08997660360581930)
© 2003 Massachusetts Institute of Technology
ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
Article PDF (393.79 KB)
Abstract

In “Isotropic Sequence Order Learning” (pp. 831864 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.