A general presentation of Artificial Eural Networks. I

Substance Use and Misuse

Volumn 32, Issue 1, 1997, Pages 97-112

  Buscema, Massimo ^a  

^a Semeion centro ricerche di scienze della communicazione   (Italy)

Author keywords

Artificial neural networks; Complex problems; Endogenous problems; Exogenous problems; Fuzzy rules; Linear; Nonlinear; Testing set; Training set

Indexed keywords

ARTICLE; ARTIFICIAL MEMBRANE; LEARNING; NERVE CELL NETWORK; NEUROSCIENCE; PRIORITY JOURNAL; SUBSTANCE ABUSE;

EID: 0031041738     PISSN: 10826084     EISSN: None     Source Type: Journal    
DOI: 10.3109/10826089709027301     Document Type: Article

References (15)

1. MARILYN McCORD NELSON and W. T. ILLINGWORTH, A Practical Guide to Neural Nets, Addison-Wesley, Reading, MA. 1991. A very easy and well-written handbook on artificial neural networks, (ANN), especially for persons who have no foundations in mathematics and statistics. It could be the first book for someone who has no idea about this subject. (A program diskette is included.)
2. T. KHANNA, Foundations of Neural Networks, Addison-Wesley, Reading, MA, 1990. A technical introduction to ANN including mathematical demonstrations of the main theorems. The presentation is limited to the most popular algorithms in the literature.
3. I. HERTZ, A. KROGH, and R. G. PALMER, Introduction to the Theory of Neural Computation, Addison-Wesley, Reading, MA. 1991. A good overview of the theoretical landscape of ANN. The basic algorithms of learning are shown and explained. The mathematical documentation is accurate and understandable for nonspecialist readers.
4. I. A. FREEMAN and DAVID M. SKAPURA, Neural Networks. Algorithms, Applications and Programming Techniques, Addison-Wesley, Reading, MA, 1991. A good basic handbook for persons who intend to develop ANN software. The main paradigms of ANN are explained, and examples of computer implementations are provided in a Pascal-like language.
5. B. KOSKO, Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall, Englewood Cliffs, NJ, 1992. A technical textbook on ANN for scholars and graduate students in this field. The mathematical aspects of ANN are very accurate and clear. Not every learning paradigm is presented.
6. P. S. CHURCHLAND and T. J. SEJNOWSKI, The Computational Brain, MIT Press, Cambridge, MA, 1992-1993. A pretty complete overview on neuroscience. Relevant attention is paid to the biological plausibility of ANN at different levels: epistemological, theoretical, and modelistic. A classic textbook on the subject.
7. DAVID E. RUMELHART and I. L. McCLELLAND, Parallel Distributed Processing. Explorations in the Micro Structure of Cognition, Volumes I and II, MIT Press, Cambridge, MA, 1986. The first most popular textbook on ANN. It is necessary reading for whoever wants to know the starting point of the main discussions on ANN and connectionism.
8. I. L. McCLELLAND and D. E. RUMELHART, Exploration in Parallel Distributed Processing. A Handbook of Models, Programs and Exercises, MIT Press, Cambridge, MA, 1988. A very useful handbook for programs interested in implementing some of the most popular ANN: Back propagation, constraint satisfactions networks, interactive activation and competition systems, etc. A program diskette is included with the source programs in C language of every ANN treated in the handbook. The software interface is very poor, but it is useful for an approach to this problem.
9. P. T. QUlLLIAM, Connectionism and Psychology: A Psychological Perspective on New Connectionism Research, Hemel Hempstead, Hawester Wheatsheaf, 1991. A very well written book on the epistemological, theoretical, and applied consequences that ANN research could have on different fields of psychology. ANN are also presented in a clear and accurate way from a technical point of view.
10. M. SMITH, Neural Networks for Statistical Modeling, Van Nostrand Reinhold, New York, NY, 1993. A practical presentation of ANN, with special attention given to the heuristic aspects of computation: how to organize data for training, how to select different learning rules, etc. Exemples of computer implementation of some ANN are provided in BASIC language. The textbook is particularly based on the family of back propagation algorithms. A very good text for the application of ANN methodology to real data.
11. D. MICHIE, D. I. SPIEGELHALTER, and C. C. TAYLOR, Machine Learning, Neural and Statistical Computation, Ellis Horwood, New York, NY, 1994. A deep and accurate comparison on classification problems between statistical, neural, and machines learning approaches. The authors define different cost functions to measure the performances of the different models. They show good expertise in statistics and in machine learning, but they don't show the same expertness in the ANN field.
12. C. M. BISHOP, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995. A very complete overview of ANN in pattern recognition.
13. B. D. RIPLEY, Pattern Recognition and Neural Networks, University of Oxford, Cambridge University Press, Cambridge, 1996. From a statistical point of view on the same subject.
14. M. A. ARBIB (Ed.), The Handbook of Brain Theory and Neural Networks, A Bradford Book, The MIT Press, Cambridge, Massachusetts, London, England, 1995. The first handbook on ANN and theory of brain. It has the structure of a dictionary. A very complete handbook, but it is quite superficial.
15. M. BUSCEMA, Self-reflexive networks, theory, topology, applications. Qual. Quan. 29(4): November 1995. An official presentation of a new and special ANN..