[go: up one dir, main page]

Denker et al., 1987 - Google Patents

Network generality, training required, and precision required

Denker et al., 1987

View PDF
Document ID
13760071628167853740
Author
Denker J
Wittner B
Publication year
Publication venue
Neural Information Processing Systems

External Links

Snippet

We show how to estimate (1) the number of functions that can be implemented by a particular network architecture,(2) how much analog precision is needed in the con (cid: 173) nections in the network, and (3) the number of training examples the network must see …
Continue reading at proceedings.neurips.cc (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/22—Arrangements for sorting or merging computer data on continuous record carriers, e.g. tape, drum, disc

Similar Documents

Publication Publication Date Title
Denker et al. Network generality, training required, and precision required
Vose Modeling simple genetic algorithms
Buckley et al. On the equivalence of neural nets and fuzzy expert systems
US5720002A (en) Neural network and method of using same
Golea et al. A growth algorithm for neural network decision trees
Gaafar et al. A neural network model for solving the lot-sizing problem
US5778153A (en) Neural network utilizing logarithmic function and method of using same
Biebighauser Testing random number generators
US5467427A (en) Memory capacity neural network
White The learning rate in back-propagation systems: An application of Newton's method
Ma et al. A comparison study of two tests for detecting initialization bias in simulation output
Li et al. A supervised clustering algorithm for computer intrusion detection
Zhang et al. Recurrent NN model for chaotic time series prediction
Lu et al. A parallel and modular multi-sieving neural network architecture for constructive learning
Park et al. Geometrical learning algorithm for multilayer neural networks in a binary field
Li Fuzzy logic systems are equivalent to feedforward neural networks
Mozer Discovering faithful'wickelfeature'representations in a connectionist network
Neubauer Robust learning algorithms for multi-layer perceptrons with discretized synaptic weights
Heistermann A parallel hybrid learning approach to artificial neural nets
Rosenhead et al. A note on robustness and interdependent decision making
Berger K-coloring vertices using a neural network with convergence to valid solutions
Kozura et al. A model of a learning neural network for data compressing
JPH0855098A (en) Neural network classifier and construction method of neural network
Hines A logarithmic neural network architecture for a PRA approximation
Obuchowicz Adaptation in a time-varying landscape using an evolutionary search with soft selection