Note on interpolation on the hypercube by means of sigma-pi neural networks

Neurocomputing

Volumn 61, Issue 1-4, 2004, Pages 471-478

  Lenze, Burkhard ^a  

^a UNIVERSITY OF APPLIED SCIENCES AND ARTS DORTMUND   (Germany)

Author keywords

Hypercube; Interpolation; Learning mode; Recall mode; Sigma pi networks

Indexed keywords

ALGORITHMS; INTERPOLATION; LEARNING SYSTEMS;

HYPERCUBES; SIGMA-PI UNITS;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CALCULATION; INFORMATION PROCESSING; LEARNING; MATHEMATICAL COMPUTING; PRIORITY JOURNAL;

EID: 10244251596     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.05.004     Document Type: Article

References (5)

1. S. Davis, Multidimensional triangulation and interpolation for reinforcement learning, in: Advances in Neural Information Processing Systems, Vol. 9, M.C. Mozer, M.I. Jordan, T. Petsche, (Eds.), MIT Press, Cambridge, MA, 1997, pp. 1005-1011.
2. Lenze B. How to make sigma-pi neural networks perform perfectly on regular training sets Neural Networks 7 8 1994 1285-1293
3. Lenze B. Hyperbolic sigma-pi neural network operators applied to image processing and reconstruction Neural Parallel Sci. Comput. 8 3&4 2000 393-400
4. Li J.-H. Michel A.N. Porod W. Analysis and synthesis of a class of neural networks: Linear systems operating on a closed hypercube IEEE Trans. Circuits Syst. 36 11 1989 1405-1422
5. D.E. Rumelhart, J.L. McClelland, Parallel Distributed Processing, Explorations in the Microstructure of Cognition, Vol. 1: Foundations, MIT Press, Cambridge, MA, 1986, second printing.