Intelligent Engineering Systems Through Artificial Neural Networks: Proceedings of the Artificial Neural Networks in Engineering (ANNIE '95) Conference, Held November 12-15, 1995, in St. Louis, Missouri, U.S.A.. Fuzzy logic and evolutionary programmingCihan H. Dagli As a follow-up to the previous four volumes of Intelligent Engineering Systems Through Artificial Neural Networks by the same editor, the present volume contains the edited versions of the technical presentations of ANNIE '95, held November, 1995 in St. Louis, Missouri. The 160-some contributions are grouped into six categories: artificial neural network architectures (including subsections on architectures and learning algorithms and training); fuzzy neural networks and systems; evolutionary programming; pattern recognition; adaptive control; and smart engineering system design (including bio-medical engineering systems; signal processing; forecasting; environmental applications; machining and robotics; process control, monitoring, and automated inspection; and general engineering). Includes bandw photographs, diagrams, and charts. Annotation copyright by Book News, Inc., Portland, OR |
Contents
The Capacity of Matcher Neural Networks | 15 |
Multivalued Neural Associative Memories | 33 |
Canonical Orders and Base Language of Fractals | 51 |
Copyright | |
59 other sections not shown
Common terms and phrases
accuracy activation function adaptive analysis application approach approximation architecture Artificial Neural Networks backpropagation behavior classification cluster CMAC coefficients complex components computed constraints convergence convex hull correlation dimension data set defined detection determine developed dynamics Engineering equation error estimate evaluation example feature feedforward frequency fuzzy logic fuzzy rules fuzzy set genetic algorithm gradient descent hidden layer hidden units identified IEEE implemented initial input vector iterations learning linear mapping Markov chain matrix measure membership functions method module multilayer perceptron mutation neural net neurons nonlinear number of hidden number of training obtained operation optimal output node paper parameters performance pixel prediction presented problem proposed random recognition reliability represent robot samples scheme selected sensors shows sigmoid function signal simulation solution space step Table techniques training data training set transform update variables wavelet weights