Neural networks - algorithms, applications, and programming techniques

@inproceedings{Freeman1991NeuralN,
  title={Neural networks - algorithms, applications, and programming techniques},
  author={James A. Freeman and David M. Skapura},
  booktitle={Computation and neural systems series},
  year={1991}
}
Freeman and Skapura provide a practical introduction to artificial neural systems (ANS). The authors survey the most common neural-network architectures and show how neural networks can be used to solve actual scientific and engineering problems and describe methodologies for simulating neural-network architectures on traditional digital computing systems. 
Approximations and adaptability of neural networks
TLDR
Given a neural network that approximates a given function, which describes some physical phenomenon, neural networks must adapt to the physical world by changing their architecture if the physical constraints and hence the given function change.
Traditional and neural networks algorithms: applications to the inspection of marble slab
TLDR
The traditional algorithms of deterministic and stochastic cluster analysis and classification are described, by comparing the results obtained using the classifiers based on neural networking techniques in supervised learning (multilayer perceptron with backpropagation).
Neural Networks and their Applications in Industry
TLDR
The article looks at the necessity of artificial intelligence and more specifically neural computing systems in today's competitive business world and the various applications that neural networks have been put to.
Survey of Neural Network Techniques and Relevant Applications
  • J. ZentnerJ. Sullins
  • Computer Science
    Proceedings. The First IEEE Regional Conference on Aerospace Control Systems,
  • 1993
TLDR
An overview of the XNET simulator and relevant applications is presented, and an attempt to enhance the currently available toolset in Control and Signal Processing by providing readers with another asset that they can bring to bear on existing and future problems.
A general presentation of artificial neural networks. I.
  • M. Buscema
  • Computer Science
    Substance use & misuse
  • 1997
TLDR
This article presents the use of a new processing technology: Artificial Neural Networks (ANN) Modeling, and introduces the reader, in an easy way, to types of problems for which researchers can use this technology.
3.14 – Neural Networks
APPLICATION OF NEURAL NETWORKS IN THE MODELING OF PLATE ROLLING PROCESSES
TLDR
This work describes some real examples of applications of neural networks in the modeling of some plate mill processes at Companhia Siderúrgica Paulista COSIPA, a Brazilian steelmaker.
A relationship between neural networks and programmable logic arrays
  • V. Eliashberg
  • Computer Science
    IEEE International Conference on Neural Networks
  • 1993
A useful relationship between some associative neural networks and programmable logic arrays (PLAs) is discussed. The analogy shown helps in understanding the properties of this class of neural
...
...

References

SHOWING 1-10 OF 59 REFERENCES
Applications of counterpropagation networks
Neural Networks and Natural Intelligence
From the Publisher: Stephen Grossberg and his colleagues at Boston University's Center for Adaptive Systems are producing some of the most exciting research in the neural network approach to making
Associative Learning, Adaptive Pattern Recognition, And Cooperative-Competitive Decision Making By Neural Networks
TLDR
It is shown that a small set of real-time non-linear neural equations within a larger set of specialized neural circuits can be used to study a wide variety of problems of associative pattern learning, adaptive pattern recognition, and parallel decision-making by neural networks.
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal
A neural network for visual pattern recognition
TLDR
A model of a neural network is presented that offers insight into the brain's complex mechanisms as well as design principles for information processors that has perfect associative recall, even for deformed patterns, without regard to their positions.
The 'neural' phonetic typewriter
TLDR
A speaker-adaptive system that transcribes dictation using an unlimited vocabulary is presented that is based on a neural network processor for the recognition of phonetic units of speech.
Learning and relearning in Boltzmann machines
This chapter contains sections titled: Relaxation Searches, Easy and Hard Learning, The Boltzmann Machine Learning Algorithm, An Example of Hard Learning, Achieving Reliable Computation with
The ART of adaptive pattern recognition by a self-organizing neural network
TLDR
Art architectures are discussed that are neural networks that self-organize stable recognition codes in real time in response to arbitrary sequences of input patterns, which opens up the possibility of applying ART systems to more general problems of adaptively processing large abstract information sources and databases.
Collective computation in neuronlike circuits.
TLDR
A number of "neural network" electronic cir­ cuits that can carry out significant computations have been studied, which offer an elegant, different way of thinking about machine computa­ tion, which is inspiring new micro­ electronic chip and computer signs and may also provide fresh insights into the biological systems.
...
...