Computer aided neural network engineering

The lack of rigorous techniques to initiate and complete in detail a neural network design renders neural network engineering to be more of an art than science. Dimensioning of neural network layers is an example of an important practical design detail typically overlooked in the neural network theoretical investigations and missed by the practitioners. We develop a computer aided neural network engineering tool based on a hybrid expert system architecture merging both knowledge-based and neurode-based components. We demonstrate our approach by mechanizing the design of counter-propagation neural network. Our automatic Kohonen layer configurator combines A* and simulated annealing search techniques to achieve both automated dimensioning and simultaneous selection of synaptic weights.

[1]  D. E. Glover.  An optical Fourier/electronic neurocomputer automated inspection system , 1988, IEEE 1988 International Conference on Neural Networks.

[2]  Lorien Y. Pratt,et al.  Comparing Biases for Minimal Network Construction with Back-Propagation , 1988, NIPS.

[3]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

[4]  Yuval Lirov.  Algorithmic multi-objective heuristics construction in the A * search , 1991, Decis. Support Syst..

[5]  Stanley C. Ahalt,et al.  Competitive learning algorithms for vector quantization , 1990, Neural Networks.

[6]  Kimmo Kaski,et al.  Variations on the Boltzmann machine , 1989 .

[7]  Shigeru Katagiri,et al.  Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2 , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[8]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[9]  H. L. Roitblat,et al.  Dolphin echolocation: identification of returning echoes using a counterpropagation network , 1989, International 1989 Joint Conference on Neural Networks.

[10]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[11]  R.J.T. Morris,et al.  A comparison of feedforward and self-organizing approaches to the font orientation problems , 1989, International 1989 Joint Conference on Neural Networks.

[12]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[13]  S. Renals,et al.  Phoneme classification experiments using radial basis functions , 1989, International 1989 Joint Conference on Neural Networks.

[14]  Maureen Caudill.  Benchmarking the performance of backpropagation and couterpropagation networks , 1988, Neural Networks.

[15]  Maureen Caudill,et al.  Comparison of internal processing of different network paradigms , 1988, Neural Networks.

[16]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[17]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[18]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[19]  G. L. Tarr,et al.  Hybrid neural networks for tactical target recognition , 1989, International 1989 Joint Conference on Neural Networks.

[20]  J. Stojanovski.  Artificial neural network for mapping , 1989, International 1989 Joint Conference on Neural Networks.

[21]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[22]  Richard Lippmann,et al.  Neural Net and Traditional Classifiers , 1987, NIPS.

[23]  Bijoy K. Ghosh,et al.  Simultaneous identification of linear systems: A heuristic approach , 1987 .

[24]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[25]  A. C. Tsoi.  Counter propagation network: an interpretation , 1989, International 1989 Joint Conference on Neural Networks.

[26]  Mark R. Bower,et al.  Neural Net Classifier For Millimeter Wave Radar , 1989, Optics & Photonics.

[27]  T.-P. Jung,et al.  Radar target identification using the learning vector quantization neural network , 1989, International 1989 Joint Conference on Neural Networks.

[28]  Anil K. Jain,et al.  39 Dimensionality and sample size considerations in pattern recognition practice , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[29]  Michael C. Mozer,et al.  Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment , 1988, NIPS.

[30]  Shigeru Katagiri,et al.  A new algorithm for representing acoustic feature dynamics , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[31]  P. K. Simpson,et al.  An investigation of neural networks for F-16 fault diagnosis. I. System description , 1989, IEEE Automatic Testing Conference.The Systems Readiness Technology Conference. Automatic Testing in the Next Decade and the 21st Century. Conference Record..

[32]  D. R. Hush,et al.  Classification with neural networks: a performance analysis , 1989, IEEE 1989 International Conference on Systems Engineering.

[33]  Ronald L. Rivest,et al.  Inferring Decision Trees Using the Minimum Description Length Principle , 1989, Inf. Comput..

[34]  D. Woods,et al.  Back and counter propagation aberrations , 1988, IEEE 1988 International Conference on Neural Networks.

[35]  Peterson.  Classification of Cm I energy levels using counterpropagation neural networks. , 1990, Physical review. A, Atomic, molecular, and optical physics.

[36]  Gerard V. Trunk,et al.  A Problem of Dimensionality: A Simple Example , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Russell C. Eberhart,et al.  Neural network PC tools: a practical guide , 1990 .

[38]  Ervin Y. Rodin.  Semantic control theory , 1988 .

[39]  Teuvo Kohonen,et al.  Statistical pattern recognition with neural networks , 1988, Neural Networks.

[40]  Robert Hecht-Nielsen,et al.  Applications of counterpropagation networks , 1988, Neural Networks.

[41]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[42]  R.J.F. Dow,et al.  Neural net pruning-why and how , 1988, IEEE 1988 International Conference on Neural Networks.

[43]  Judea Pearl,et al.  Heuristics : intelligent search strategies for computer problem solving , 1984 .

[44]  John S. Denker,et al.  Network Generality, Training Required, and Precision Required , 1987, NIPS.

[45]  Gregory L. Tarr.  Dynamic Analysis of Feedforward Neural Networks Using Simulated and Measured Data , 1988 .