19-07-2011, 04:05 PM
[attachment=14661]
ANN – What does it mean?
The complex neural structure inside the human brain forms a massive parallel
information system ,the basic processing unit is the NEURON. This contrasts with
conventional computers in which a single processor executes a series of instructions
Neuro - Computing is something called the brain-like computations.
It is composed of a large number of highly interconnected processing
elements (neurons) working in unison to solve specific problems.
From a mathematical point of view ANN, is a complex non-linear function
with many parameters that are adjusted (calibrated, or trained) in such a way
that the ANN output becomes similar to the desired output.
History
The first step toward artificial neural networks came in 1943
when Warre McCulloch, a neurophysiologist, and a young
mathematician, Walter Pitts, wrote a paper on how neurons
might work. They modeled a simple neural network with
electrical circuits
Characteristics of the ANN
The NNs exhibits mapping capabilities, that is they can map input patterns
to their associated output patterns.
The NNs learns by example. Thus NN architectures can be “trained” with
known examples of the specific problem before they are tested for their
inference capability to unknown instance of the problem.
The NNs can process information in parallel, at high speed.
Learning of Ann
Supervised learning.
Unsupervised learning.