Artificial neural networks

Artificial Neural Networks Technology
Table of Contents
Postscript Version[2.8MB] - Text Version][193k] Title Page
List of Tables and Figures ...

Artificial neural networks (ANN) are among the newest signal-processing technologies in the engineer's toolbox. The field is highly interdisciplinary, but our approach will restrict the view to the engineering perspective.

Artificial neural networks have proved useful in a variety of real-world applications that deal with complex, often incomplete data. The first of these were in visual pattern recognition and speech recognition.

Artificial Neural Networks
Add your Opinion!
There are tens of thousands of h2g2 Guide Entries, written by our Researchers. If you want to be able to add your own opinions to the Guide, simply become a member as an h2g2 Researcher.

Artificial Neural Networks
The branch of AI that modeled its work after the neural network of the human brain is called connectionism.

Artificial neural networks: Computers whose architecture is modeled after the brain. They contain idealized neurons called nodes which are connected together in some network.

Artificial Neural Networks
Artificial Neural Networks (ANN) are computational-cognitive models based on the structure of the nervous system.

Artificial Neural Networks
This technique has been applied to many of the difficult problems in AI with some success.

Artificial neural networks: Non-linear predictive models that learn through training and resemble biological neural networks in structure.

Artificial Neural Networks (ANN)
An ANN is an interconnected network of very simple calculating units called neurons. Every connection in the network is assigned a weight which specifies the extent of possible influence.

Artificial Neural Networks
Performance comparison of neural network algorithms tested on UCI data sets
A close view to Artificial Neural Networks Algorithms
Neural Networks at the Open Directory Project ...

Artificial neural networks (ANNs) are computer system developed to mimic the operations of human brain by mathematically modeling its neurophysiological structure (i.e., nerve cells and the network of interconnections between them).

Artificial neural networks are information processing systems composed of a large number of highly interconnected processing elements (modelled on neurons in the brain) linked by weighted connections (mirroring synapses).
Ontology ...

Artificial Neural Networks in Healthcare: A Short Review
Margarita Sordo's paper, Introduction to Neural Networks in Healthcare, ...

Yeah, we've built "artificial neural networks", but most of those are research simulations! ...

Many practical applications are dependent on artificial neural networks, networks that pattern their organization in mimicry of a brain's neurons, which have been found to excel in pattern recognition.

Even with these inhibiting factors, artificial neural networks have presented some impressive results.

* "On the Analysis of Pyrolysis Mass Spectra Using Artificial Neural Networks: Individual Input Scaling Leads to Rapid Learning" by Mark J. Neal, Royston Goodacre and Douglas B. Kell, from the University of Wales in the United Kingdom.

Most researchers today would agree that artificial neural networks are quite different from the brain in terms of structure.

The pattern recognition aspects of Artificial Neural Networks don't really explain too much about how real brains actually work.

The field goes by many names, such as connectionism, parallel distributed processing, neuro-computing, natural intelligent systems, machine learning algorithms, and artificial neural networks.

trainable weight In artificial neural networks that use weighted connections, some of those connections may have fixed values - i.e. they are specified as not being subject to change when the network is trained, e.g.

Donald O. Hebbs suggested a way in which artificial neural networks might learn.
1950
Turing proposed his test, the Turing test, to recognize machine intelligence.

Patterson, D. (1996). Artificial Neural Networks. Singapore: Prentice Hall. Good wide-ranging coverage of topics, although less detailed than some other books.

Trained on randomly selected patches of an image (150,000 training steps). It was then tested on the entire image patch by patch using the entire set of non overlapping patches See "Fundamentals of Artificial Neural Networks", Hassoun, pp247-253.

6 Artificial Neural Networks
6.1 Introduction, Or How The Brain Works
6.2 The Neuron As A Simple Computing Element
6.3 The Perceptron
6.4 Multilayer Neural Networks
6.5 Accelerated Learning In Multilayer Neural Networks
6.6 The Hopfield Network
6.

See also: Neural network, Artificial neural network, Artificial intelligence, Knowledge, AI