A nonlinear learning network model for continuous

Abstract A nonlinear network model with continuous learning capability is described. The dynamically capacity allocating (DCA) network model is able to learn incrementally as more information becomes available and to avoid the spatially unselective forgetting of commonly used learning algorithms. The DCA networks are an extension of kernel estimation methods with a learning algorithm that selects automatically the number of necessary basis functions in the model. This learning algorithm is a fast noniterative method and therefore it is suitable for large scale implementations of continuously learning systems even on conventional computer hardware.

[1]  James Demmel,et al.  The geometry of III-conditioning , 1987, J. Complex..

[2]  John E. Moody,et al.  Fast Learning in Multi-Resolution Hierarchies , 1988, NIPS.

[3]  Dennis J. Volper,et al.  Quadratic function nodes: Use, structure and training , 1990, Neural Networks.

[4]  B. Ydstie.  Forecasting and control using adaptive connectionist networks , 1990 .

[5]  A. Lapedes,et al.  Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[6]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[7]  C. J. Stone,et al.  Optimal Global Rates of Convergence for Nonparametric Regression , 1982 .

[8]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[9]  Tomaso A. Poggio,et al.  Extensions of a Theory of Networks for Approximation and Learning , 1990, NIPS.

[10]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[11]  James P. Crutchfield,et al.  Geometry from a Time Series , 1980 .

[12]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[13]  R. Franke.  Scattered data interpolation: tests of some methods , 1982 .

[14]  C. J. Stone,et al.  Additive Regression and Other Nonparametric Models , 1985 .

[15]  M. B. Priestley,et al.  Non-linear and non-stationary time series analysis , 1990 .

[16]  Farmer,et al.  Predicting chaotic time series. , 1987, Physical review letters.

[17]  Manoel Fernando Tenorio,et al.  Self-organizing network for optimum supervised learning , 1990, IEEE Trans. Neural Networks.

[18]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[19]  A. Lapedes,et al.  Nonlinear Signal Processing Using Neural Networks , 1987 .

[20]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[21]  N. V. Bhat,et al.  Use of neural nets for dynamic modeling and control of chemical process systems , 1990 .

[22]  Gene H. Golub,et al.  Matrix computations , 1983 .