Proceedings of the 1985 Symposium on Security and Privacy, April 22-24, 1985, Oakland, California
Antônio de Pádua Braga, Teresa Bernarda Ludermir
IEEE Computer Society Press, 1985 - Computers - 241 pages
Contains 46 papers and posters from a December 1998 symposium. Subjects include improving back-propagation with sliding mode control, learnability in sequential RAM-based neural networks, unsupervised neural network learning for blind sources separation, optimizations of the combinatorial neural model, extracting rules from feedforward Boolean neural networks, factor semantics for document retrieval, and artificial neural networks applied to theoretical chemistry. No index. Annotation copyrighted by Book News, Inc., Portland, OR.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Improving Backpropagation with Sliding Mode Control
Training Linear Neural Network with Early Stopped Learning and Ridge Estimation
Learnability in Sequential RAMbased Neural Networks
20 other sections not shown
Other editions - View all
activation adaptive analysis application approach approximation architecture Artificial Neural Networks backpropagation Boolean Box-Jenkins censor classifier components connections considered convergence coprocessor corresponding data set defined digits eigenfaces energy equation error evaluated fault feature feedforward Figure FPGA fuzzy Gaussian Genetic Algorithms GMDH HCPRs hidden layer IEEE implementation initial input layer input vector Kohonen's learning algorithm learning rate learning rule linear mapping matrix memory method multilayer Multilayer Perceptron musical sequence neurons nodes nonlinear obtained operation optimal output layer paper parameters Perceptron performance phrase pixel presented problem proposed Q-learning radial basis function radial unit random RBFN representation represented robot samples segmentation sequence shown signal simulation solution space Sparse Distributed Memory SWNN synaptic Table techniques telephone numbers tion topology training set trajectory unit centers unsupervised unsupervised learning update values variables Vector Quantization wavelet weight vector zero