• Corpus ID: 60577818

Neural Networks: A Comprehensive Foundation

@inproceedings{Hyakin1994NeuralNA,
  title={Neural Networks: A Comprehensive Foundation},
  author={S. Hyakin},
  year={1994}
}
  • S. Hyakin
  • Published 1994
  • Computer Science, Biology
Simon Haykin Neural Networks A Comprehensive Foundation. Neural Networks A Comprehensive Foundation Simon S. Neural Networks A Comprehensive Foundation Simon S. Neural Networks A Comprehensive Foundation. Neural Networks Association for Computing Machinery. Book Review Neural Networks A Comprehensive Foundation. Neural Networks A Comprehensive Foundation Pearson. Neural networks a comprehensive foundation. Neural Networks a Comprehensive Foundation AbeBooks. Neural networks a comprehensive… 
U-6 Integration of Neural Networks , Fuzzy Logic , and Genetic Algorithms
  • Computer Science
Integration of Neural Networks, Fuzzy Logic, and Genetic Algorithms Chapter 101 Neural networks, fuzzy logic, and genetic algorithms are soft computing methods which have been inspired by biological
Neural Network Modeling of Financial Markets
TLDR
It was concluded that neural networks do have the capability to forecast financial markets and, if properly trained, the individual investor could benefit from the use of this forecasting tool.
Towards Compact Neural Networks
TLDR
The main goal is to improve the original weight discretization technique as much as possible to obtain networks with both a small number of neurons and a large number of connections, which is of great importance for hardware implementation of neural networks.
A SURVEY ON NEURAL NETWORK MODELS FOR DATA ANALYSIS
TLDR
An attempt is made to study the various ANN suitable for clustering with an accuracy similar to the best statistical methods and which are characterized by parallel processing, a distributed architecture, and a large number of nodes, at the same time capable of proposing an optimal number of groups into which the patterns may be clustered.
Fundamentals of Artificial Neural Networks [Book Reviews]
  • T. Fine
  • Computer Science
    IEEE Transactions on Information Theory
  • 1996
TLDR
Neural networks provided a wide spectrum of applied statisticians with a new and powerful class of regression and classification functions that, for the first time, allowed them to make successful truly nonlinear models involving hundreds of variables.
Non Deterministic Processing in Neural Networks : An Introduction to Multi-Threaded Neural Networks
TLDR
This paper attempts to explain how multithreaded neural networks can be used as a basis for building parallel networks and outlines some biological foundations and introduces some approaches that may be used to recreate software implementations of concurrent artificial neural networks.
Cooperative coevolution of artificial neural network ensembles for pattern classification
TLDR
This paper proposes a general framework for designing neural network ensembles by means of cooperative coevolution, and applies the proposed model to ten real-world classification problems of a very different nature from the UCI machine learning repository and proben1 benchmark set.
Heuristic principles for the design of artificial neural networks
A reference model approach to stability analysis of neural networks
TLDR
A novel methodology called a reference model approach to stability analysis of neural networks is proposed, to study a neural network model with reference to other related models, so that different modeling approaches can be combinatively used and powerfully cross-fertilized.
An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems
TLDR
The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature.
...
...

References

SHOWING 1-3 OF 3 REFERENCES
@BULLET A set of pairs, consisting of an input and the corresponding desired response, form a set of training data or training sample
  • @BULLET A set of pairs, consisting of an input and the corresponding desired response, form a set of training data or training sample
Threshold function φ(v) = 1, v ≥ 0
  • Threshold function φ(v) = 1, v ≥ 0
@BULLET The examples can be: -labeled, with a known desired response (target output) to an input signal. -unlabeled, consisting of different realizations of the input signal
  • @BULLET The examples can be: -labeled, with a known desired response (target output) to an input signal. -unlabeled, consisting of different realizations of the input signal