On the approximation of a quadratic map by a small neural network

Neurocomputing

Volumn 12, Issue 4, 1996, Pages 313-326

  Saxén, Henrik ^a  

^a ÅBO AKADEMI UNIVERSITY   (Finland)

Author keywords

Analytical weight constraints; Feedforward neural network; Quadratic map

Indexed keywords

APPROXIMATION THEORY; CHAOS THEORY; CONSTRAINT THEORY; ITERATIVE METHODS; TIME SERIES ANALYSIS;

ANALYTICAL WEIGHT CONSTRAINTS; CHAOTIC TIME SERIES; QUADRATIC MAP;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL;

EID: 0030221793     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/0925-2312(95)00064-X     Document Type: Article

References (20)

1. [1] R. Battiti, First-and second-order methods for learning: Between steepest descent and Newton's method, Neural Computat. 4 (1992) 141-166.
2. [2] E.K. Blum and X. Wang, Stability of fixed points and periodic orbits and bifurcations in analog neural networks. Neural Networks 5 (1992) 577-587.
3. [3] D.S. Broomhead and D. Lowe, Multivariable functional interpolation and adaptive networks, Complex Systems 2 (1988) 321-355.
4. [4] A.B. Bulsari and H. Saxén, A recurrent network for modeling noisy temporal sequences, Neurocomputing 7 (1995) 29-40.
5. [5] G. Cybenko, Approximation by superpositions of a sigmoidal function Mathematics of Control, Signals, and Systems 2 (1989) 303-314.
6. [6] M. Feigenbaum, Universal behavior of nonlinear systems, Physica D 7 (1983) 16-39.
7. [7] R. Fletcher, Practical Methods of Optimization, Vol. 1 (John Wiley & Sons, Chichester, 1980).
8. [8] K. Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks 2 (1989) 183-192.
9. [9] C. de Groot and D. Würtz, Analysis of univariate time series with connectionist nets: A case study of two classical examples, Neurocomputing 3 (1991) 177-192.
10. [10] E. Hartman and J.D. Keeler, Predicting the future: Advantages of semilocal units, Neural Computation (1991) 566-578.
11. [11] K. Hornik, M. Stinchombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989) 359-366.
12. [12] K. Hornik, M. Stinchombe and H. White, Universal approximation of an unknown mapping and its derivatives using neural nets, Neural Networks 3 (1990) 551-560.
13. [13] P. Jokinen, A nonlinear network model for continuous learning, Neurocomputing 3 (1991) 157-176.
14. [14] P. Koiran, On the complexity of approximating mappings using feedforward networks, Neural Networks 6 (1993) 649-654.
15. [15] A. Lapedes and R. Farber, Nonlinear signal processing using neural networks: Prediction and system modelling, Technical Report UR-87-2662, Los Alamos, USA, 1987.
16. [16] G.J. Mpitsos, R.M. Burton, Jr. and H.C. Creech, Connectionist networks learn to transmit chaos, Brain Research Bulletin 21 (1988) 539-546.
17. [17] S. Renals and R. Rohwer, A study of networks dynamics, J. Statistical Physics 58 (1990) 825-848.
18. [18] X. Wang, Period doublings to chaos in a simple neural network: An analytical proof, Complex Systems 5 (1991) 425-441.
19. [19] A.S. Weigend, B.A. Huberman and D.E. Rumelhart, Predicting the future: A connectionist approach, Int. J. Neural Systems 1 (1990) 193-209.
20. [20] B.E. Ydstie, Forecasting and control using adaptive connectionist networks, Computers Chem. Engng. 14 (1990) 583-599.