Studies of Mind and Brain pp 157-193 | Cite as
Pattern Learning by Functional-Differential Neural Networks with Arbitrary Path Weights
Abstract
This paper proves the universal theorem on associative learning that culminates my 1967–1972 articles on this subject. The theorem is universal in the following sense. It says that if my associative learning laws were invented at a prescribed time during the evolutionary process, then they could be used to guarantee unbiased associative learning in essentially any later evolutionary specialization. That is, the laws are capable of learning arbitrary spatial patterns in arbitrarily many, simultaneously active sampling channels that are activated by arbitrary continuous data preprocessing in an essentially arbitrary anatomy. The learning of arbitrary space-time patterns is also guaranteed given modest requirements on the temporal regularity of stimulus sampling, as in avalanches and generalizations thereof.
Keywords
Conditioned Stimulus Associative Learning Pattern Learning Pattern Discrimination Path WeightPreview
Unable to display preview. Download preview PDF.
References
- [1]Grossberg, S., ‘Embedding Fields: Underlying Philosophy, Mathematics, and Applications to Psychology, Physiology, and Anatomy’, J. of Cybernetics 1 (1971), 28.CrossRefGoogle Scholar
- [2]Grossberg, S., ‘Neural Pattern Discrimination’, J. of Theoretical Biology 27 (1970), 291.CrossRefGoogle Scholar
- [3]Grossberg, S., ‘Neural Expectation: Cerebellar and Retinal Analogs of Learnable and Unlearned Pattern Classes’, Kybernetik 10 (1972), 49.CrossRefGoogle Scholar
- [4]Grossberg, S., ‘On the Dynamics of Operant Conditioning’, J. of Theoretical Biology 33 (1971), 225.CrossRefGoogle Scholar
- [5]Grossberg, S., ‘On the Serial Learning of Lists’, Math. Biosci. 4 (1969), 201.CrossRefGoogle Scholar
- [6]Grossberg, S. and J. Pepe, ‘Spiking Threshold and Overarousal Effects in Serial Learning’, J. of Statistical Physics 3 (1971), 95.CrossRefGoogle Scholar
- [7]Grossberg, S., ‘Pavlovian Pattern Learning by Nonlinear Neural Networks’, Proc. of the Natl Acad, of Science, U.S.A. 68 (1971), 68.CrossRefGoogle Scholar
- [8]Grossberg, S., ‘On Learning and Energy-Entropy Dependence in Recurrent and Nonrecurrent Signed Network’, J. of Statistical Physics 1 (1969), 319.CrossRefGoogle Scholar
- [9]Grossberg, S., ‘A Neural Theory of Punishment and Avoidance, I. Qualitative Theory’, Math. Biosci., in press.Google Scholar
- [10]Grossberg, S., ‘A Neural Theory of Punishment and Avoidance, II. Quantitative Theory’, Math. Biosci., in press.Google Scholar
- [11]Kimble, G. A., Foundations of Conditions and Learning, Appleton-Century-Crafts, New York, 1967, p. 26.Google Scholar
- [12]Grossberg, S., ‘Some Networks That Can Learn, Remember, and Reproduce any Number of Complicated Patterns, II’, Studies in Applied Math. XLIX (1970), 137.Google Scholar
- [13]Grossberg. S., ‘A Prediction Theory for some Nonlinear Functional-Differential Equations, I’, J. Math. Anal, and Applies. 21 (1968), 643.CrossRefGoogle Scholar
- [14]Grossberg, S., ‘A Prediction Theory for Some Nonlinear Functional-Differential Equations, II’, J. Math. Anal, and Applies. 22 (1968), 490.CrossRefGoogle Scholar
- [15]Grossberg, S., ‘On the Global Limits and Oscillations of a System of Nonlinear Differential Equations Describing a Flow on a Probabilistic Network’, J. Diff. Eqns. 5 (1969), 531.CrossRefGoogle Scholar
- [16]Ruch, T. C., H. D. Patton, J. W. Woodbury, and A. L. Towe, Neurophysiology, W. B. Saunders, Philadelphia, 1961.Google Scholar