Showing papers on "Unsupervised learning published in 1971"
TL;DR: The results of experiments in which an unsupervised net is found to perform a natural-clustering operation are reported, and the net is randomly connected with outputs feeding back to inputs.
Abstract: This letter reports the results of experiments in which an unsupervised net is found to perform a natural-clustering operation. An `aging? process is introduced during learning, and the net is randomly connected with outputs feeding back to inputs.
17 citations
TL;DR: The discrete data case is considered, and the discrete data version of the partition theorem is derived, and several examples are presented of the application of the adaptive detectors.
Abstract: In a previous paper [1], Bayes-optimal recursive supervised learning structure and parameter adaptive pattern recognition systems were derived for continuous "lumped" Gaussian processes. In this paper, the discrete data case is considered, and the discrete data version of the partition theorem is derived. Several examples are also presented of the application of the adaptive detectors, and computational results are given indicating their learning capacity and convergence rate.
8 citations
01 Jan 1971
7 citations
TL;DR: A new formulation of the problem of structure and parameter adaptive pattern recognition with supervised learning yielding significant computational advantages is presented.
Abstract: A new formulation of the problem of structure and parameter adaptive pattern recognition with supervised learning yielding significant computational advantages is presented.
5 citations
01 Dec 1971
TL;DR: This paper considers supervised learning, structure and parameter adaptive binary pattern recognition when a nongaussian pattern is observed in gaussian noise and certain judicious approximations are made use of.
Abstract: This paper considers supervised learning, structure and parameter adaptive binary pattern recognition when a nongaussian pattern is observed in gaussian noise. To facilitate a feasible solution, certain judicious approximations are made use of. Two examples are presented to demonstrate the learning capability of the proposed algorithms.
1 citations
TL;DR: Methods of Estimation Theory are used to show that reinforcement learning is implemented by sequential parameter estimation which alters both a priori and spontaneously learned templates feature by feature.
01 Jan 1971
TL;DR: The authors have developed an experimental random machine which can be effectively applied to the analysis of a system governed by algebraic or differential equations.
Abstract: A random machine, [1, 2] in which the random pulse frequency is used as the machine variable, may be considered to be somewhere between an analog and a digital computer in speed and accuracy of operation and to perform functions similar to those of the brain. The authors have developed an experimental random machine which can be effectively applied to the analysis of a system governed by algebraic or differential equations.