Abstract

this paper. Let us place it within the neural network perspective, and particularly that of learning. The area of neural networks has greatly benefited from its unique position at the crossroads of several diverse scientific and engineering disciplines including statistics and probability theory, physics, biology, control and signal processing, information theory, complexity theory, and psychology (see [45]). Neural networks have provided a fertile soil for the infusion (and occasionally confusion) of ideas, as well as a meeting ground for comparing viewpoints, sharing tools, and renovating approaches. It is within the ill-defined boundaries of the field of neural networks that researchers in traditionally distant fields have come to the realization that they have been attacking fundamentally similar optimization problems.

Citations

7468	D.B.: Maximum likelihood from incomplete data via the em algorithm - Dempster, Laird, et al. - 1977
3765	Pattern Classification and Scene Analysis - Duda, Hart - 1973
3482	Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images - Geman, Geman - 1984
3280	Optimization by simulated annealing - Kirkpatrick, Gelatt, et al. - 1983
3237	Neural networks: a comprehensive foundation - Haykin - 1994
2058	Equation of state calculations by fast computing machines - Metropolis, Rosenbluth, et al. - 1953
1673	Some methods for classification and analysis of multivariate observations - MacQueen - 1967
1566	A new look at the statistical model identification - Akaike - 1974
1539	Vector quantization and signal compression - Gersho, Gray - 1994
1365	Clustering Algorithms - Hartigan - 1975
1360	Information Theory and Reliable Communication - Gallager - 1968
1107	An algorithm for vector quantizer design - Linde, Buzo, et al. - 1980
750	Least Squares Quantization in PCM - Lloyd - 1982
732	Adaptive mixtures of local experts - Jacobs, Jordan, et al. - 1991
714	A maximization technique occuring in the statistical analysis of probabalistic functions in markov chains - Baum, Petrie, et al. - 1970
703	Hierarchical mixtures of experts and the EM algorithm - Jordan, Jacobs - 1994
601	Information theory and statistical mechanics - Jaynes - 1957
595	Statistical analysis of finite mixture distributions. Wiley Series in Probability and Mathematical Statistics: Applied Probability and Statistics - Titterington, Smith, et al. - 1985
441	Mixture models: Inference and applications to clustering - G, Basford - 1988
385	The mathematical theory of communication. Bell Syst - Shannon - 1948
256	A graduated assignment algorithm for graph matching - Gold, Rangarajan - 1996
252	A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters - Dunn - 1973
241	Neural-Gas” network for vector quantization and its application to time-series prediction - M, Berkovich, et al. - 1993
241	Stochastic complexity and modeling - Rissanen - 1986
192	Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy - Shore, Johnson - 1980
189	Quantizing for minimum distortion - Max - 1960
187	Pairwise data clustering by deterministic annealing - Hoffmann, Buhmann - 1997
179	Rate Distortion Theory - Berger - 1971
171	Computation of Channel Capacity and Rate-Distortion Function - Blahut - 1972
161	D.: An analogue approach to the travelling salesman problem using an elastic net method. Nature 326 - Durbin, Willshaw - 1987
138	Parallel and deterministic algorithms from MRF's: surface reconstruction - Geiger, Girosi - 1991
136	Entropy-constrained vector quantization - Chou, Lookabaugh, et al. - 1989
131	Neural networks and related methods for classification - Ripley
118	A study of vector quantization for noisy channels - Farvardin - 1990
95	Statistical pattern recognition with neural networks: Benchmarking studies - Chrisley - 1988
89	A deterministic annealing approach to clustering - Rose, Gurewitz, et al. - 1990
86	Hedonic prices and the demand for clean air - Harrison, Rubinfeld - 1978
77	Nonlinear gated experts for time-series: Discovering regimes and avoiding overfitting - Weigend, S, et al. - 1995
75	A clustering technique for summarizing multivariate data - Ball, Hall - 1967
69	On the performance and complexity of channel optimized vector quantizers - Farvardin, Vaishampayan - 1991
64	Regression modeling in back-propagation and projection pursuit learning - Hwang, Lat, et al. - 1994
63	A convergence theorem for the fuzzy ISODATA clustering algorithms - Bezdek
63	Optimal partitioning for classification and regression trees - Chou - 1991
63	On the training of radial basis function classifiers. Neural networks - Musavi, Ahmed, et al. - 1992
54	Learning piecewise control strategies in a modular neural network architecture - Jacobs, Jordan - 1993
53	Modestino, “Optimum quantizer performance for a class of non-Gaussian memoryless sources - Farvardin, W - 1984
52	Vector quantization with complexity costs - Buhmann, Kühnel
49	A construction of vector quantizers for noisy channels - Kumazawa, Kasahara, et al. - 1984
47	An Analysis of the Elastic Net Approach to the Traveling Salesman Problem - Durbin, Szeliski, et al. - 1989
46	Generalised deformable models, statistical physics and matching problems - Yuille - 1990