Neural trees: a new tool for classification

References

• Rumelhart D E, McClelland J L. Parallel Distributed Processing. D E Rumelhart, J L McClelland. MIT Press, Cambridge, MA 1986; 1
   Google Scholar
• Lippmann R P. An introduction to computing with neural nets. IEEE ASSP Magazine 1987; 3: 4–22
   Google Scholar
• Le Cun Y. A learning scheme for asymetric threshold networks. Cognitiva 1985, D Eter, 1985; 599–604, (CEFSA-AFCET)
   Google Scholar
• Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation. Parallel Distributed Processing, D E Rumelhart, J L McClelland. MIT Press, Cambridge, MA 1986; 1
   Google Scholar
• Werbos P J. Beyond regression: new tools for prediction and analysis in behavioural science. Harvard University. 1974, PhD Thesis
   Google Scholar
• Sejnowski T J, Rosenberg C R. Parallel networks that learn to pronounce English text. Complex Systems 1987; 1: 145–68
   Google Scholar
• Duranton M, Sirat J A (1986) Learning on VLSI: a general purpose digital neurochip. Proc. Int. Joint Conf. on Neural Networks, Washington DC, June, 18–221989. IEEE, Piscataway, NJ, 2: 613, Duranton M., and Mauduit, 1989 Learning on VLSI: A general purpose digital neurochip Proc. 1st IEE Conf. on Artificial Neural Nets (London, 16–18 October 1989) (London: IEE) pp 62–6
   Google Scholar
• Rujan P, Marchand M. Learning by minimizing resources in neural networks. Complex Systems 1989; 3: 229–42, Marcand M, Golea M and Rujan P 1990 Convergence theorem for sequential learning in two layer perceptrons Europhys. Lett. 11 487–92
   Google Scholar
• Bichsel M, Seitz P. Minimum class entropy: a maximum information approach to layered networks. Neural Networks 1989; 2: 133–41
   Web of Science ®Google Scholar
• Gallant S I (1986) Three constructive algorithms for network learning. Proc. 8th Ann. Conf. of Cognitive Science Society, Amherst, MA, August, 15–171986, 652–60
   Google Scholar
• Mézard M, Nadal J-P. Learning in feedforward neural networks: the tiling algorithm. J. Phys. A: Math. Gen. 1989; 22: 2191–203
   Google Scholar
• Nadal J-P. Study of a growth algorithm for a feedforward network. Int. J. Neural Systems 1989; 1: 55–9
   Google Scholar
• Knerr S, Personnaz L, Dreyfus G. Single-layer learning revisited: A stepwise procedure for building and training a neural network. Neurocomputing: Algorithms, Architectures, and Applications. NATO ASI Series, Springer, Berlin 1990
   Google Scholar
• Hougen D R, Omohundro S M. Fast texture recognition using information trees. Department of Computer Science, University of Illinois at Urbana-Champaign. 1988, Report, Omohundro S M 1987 Efficient algorithm with neural network behavior Complex Systems 1 273–347
   Google Scholar
• Gross D. Induction and ID3: more powerful than we think. Expert Systems 1988; 5: 348–50
   Google Scholar
• Gallant S I (1986) Optimal linear discriminants. Proc 8th Int. Conf. on Pattern Recognition, Paris, October, 27–311986. IEEE Computer Society, Washington, DC, 849–52
   Google Scholar
• Minsky, Papert S. Perceptrons. MIT Press, Cambridge, MA 1969
   Google Scholar
• Willshaw D J, Buneman O P, Longuet-Higgins H P. Non-holographic associative memory. Nature 1969; 222: 960–2
   PubMed Web of Science ®Google Scholar
• Nadal J-P, Toulouse G. Information storage in sparsely coded memory nets. Network 1990; 1: 61–74
   Web of Science ®Google Scholar
• Schmitz H J, Pöppel G, Wünsch F, Krey U. Fast recognition of real objects by an optimized hetero-associative neural network. J. Physique 1990; 51: 167–83
   Google Scholar
• Linsker R. Self-organization in a perceptual network. Computer 1988; 21: 105–17
   Web of Science ®Google Scholar
• Oja E. Neural networks, principal components, and subspaces. Int. J. Neural System 1989; 1: 61–8
   Google Scholar
• Siral J A. A fast neural algorithm for principal-value decomposition and singular-value decomposition. Int. J. Neural Networks 1990, Submitted
   Google Scholar
• Makram-Ebeid S, Sirat J A, Vialat J-R (1989) A rationalized error backpropagation algorithm. Proc. Int. Joint Conf. on Neural Networks, Washington, DC, June, 18–221989. IEEE, Piscataway, NJ, 2: 373–80
   Google Scholar
• Tesauro G, Janssens B. Scaling relationships in backpropagation learning. Comptex Systems 1988; 2: 39–44
   Google Scholar
• Huffman D A. A method for the construction of minimum-redundancy codes. Proc. IRE 1952; 10: 1098–101
   Google Scholar
• Kohonen T. Self-Organization and Associative Memory. Springer, Berlin 1984
   Google Scholar
• Bourlard H. Philips Research Laboratories, Brussels 1988, personal communication
   Google Scholar
• Vallet F, Cailton J-G, Refregier Ph. Linear and non-linear extension of the pseudo-inverse solution for learning Boolean functions. Europhys. Lett. 1989; 9: 315–20
   Google Scholar
• Hopfield J J. Learning algorithms and probability distributions in feed-forward and feed-back networks. Proc. Natl. Acad. Sci. USA 1987; 84: 8429–33
   PubMed Web of Science ®Google Scholar
• Hinton G E, Sejnowski T J. Learning and relearning in Boltzmann machines. Parallel Distributed Processing, D E Rumelhart, J L McClelland. MIT Press, Cambridge, MA 1986; 1: 282–317
   Google Scholar
• Gallant S I. 1990, private communication
   Google Scholar
• Golea M, Marchand M. A growth algorithm for neural network decision trees. Europhys. Lett. 1990; 12: 205–10
   Google Scholar