An important problem in pattern recognition or signal detection is the recognition of a pattern that is completely characterized statistically except for a finite set of unknown parameters. If a machine is required to solve such a problem on a number of occasions, it is possible to take advantage of this repetition. One can design a machine that will extract more and more of the pertinent information about these unknown parameters as it recognizes the patterns and readjusts itself to be more selective to them; the machine improves in performance as it gains experience on the problem. This paper presents a model suitable for many such problems and evolves a solution in the form of a machine that "learns" to solve the problem without external aid. Such machines are said to "learn without a teacher." The Bayes solution to the model problem requires the computation of the a posteriori probability density of the unknown parameters. A recursive equation for this density is derived. This equation describes the structure of a relatively simple system of finite size that may be realized in a delay-feedback form. The application of the model and the synthesis of a learning system are illustrated by the derivation of a receiver for the detection of signals of unknown amplitude in white Gaussian noise.
[1]
E. M. Glaser,et al.
Signal detection by adaptive filters
,
1961,
IRE Trans. Inf. Theory.
[2]
R. F. Daly.
ADAPTIVE BINARY DETECTORS
,
1961
.
[3]
Norman M. Abramson,et al.
Learning to recognize patterns in a random environment
,
1962,
IRE Trans. Inf. Theory.
[4]
David B. Cooper,et al.
Adaptive Pattern Recognition and Signal Detection Using Stochastic Approximation
,
1964,
IEEE Trans. Electron. Comput..
[5]
David B. Cooper,et al.
Nonsupervised Adaptive Signal Detection and Pattern Recognition
,
1964,
Inf. Control..
[6]
Henry Johnston Scudder,et al.
Adaptive communication receivers
,
1965,
IEEE Trans. Inf. Theory.
[7]
J. C. Hancock,et al.
The non-supervised learning of probability spaces and recognition of patterns.
,
1965
.
[8]
J. Spragins,et al.
A note on the iterative application of Bayes' rule
,
1965,
IEEE Trans. Inf. Theory.
[9]
David Middleton,et al.
Adaptive detection of statistical signals in noise
,
1966,
IEEE Trans. Inf. Theory.