Neural networks have a large appeal to many researchers due to their great closeness to the structure of the brain, a characteristic not shared by more traditional systems.

In an analogy to the brain, an entity made up of interconnected neurons, neural networks are made up of interconnected processing elements called units, which respond in parallel to a set of input signals given to each. The unit is the equivalent of its brain counterpart, the neuron.

A neural network consists of four main parts:

1. Processing units{uj}, where each uj has a certain activation level aj(t) at any point in time.

2. Weighted interconnections between the various processing units which determine how the activation of one unit leads to input for another unit.

3. An activation rule which acts on the set of input signals at a unit to produce a new output signal, or activation.

4. Optionally, a learning rule that specifies how to adjust the weights for a given input/output pair.

A processing unit uj takes a number of input signals, say a1j, a2j,...,anj with corresponding weights w1j, w2j,...,wnj, respectively. The net input to uj given by:

netj = SUM (wij * aij)

The new state of activation of uj given by:

aj(t+1) = F(aj(t),netj),

where F is the activation rule and aj(t) is the activation of uj at time t. The output signal oj of unit uj is a function of the new state of activation of uj:

oj(t+1) = fj(aj(t+1)).

One of the most important features of a neural network is its ability to adapt to new environments. Therefore, learning algorithms are critical to the study of neural networks.

Also they are diferent architectures of a Neural Network some are they diferents but esencially works with the same fundaments they exists with diferent capabilites and implementations.

Some neural networks is more algorithms than neural networks. Why don't to try emulate some simple neural sistem of bee or somthing more simpler with artificial neural networks?

I think that neural algorithms are used more in evolutionary programming than in genetic algorithms to predict subject's optimal representation within several generations that can later determine the rate of mutation and recombinations associated with that particular phenotype.
Probably artificial networks are designed for logistics and cognitive wave "the objective patterns" in the brain since it deals more with processing than fitness functions.

I've been working on a "neural pathway" theory myself, and have just started to look into neural networks. Let me give a very brief explanation of my neural pathway first.

Basically, the psychological functions of the brain operate on a "checks and balance" system and go through a series of checkpoints before the physical expression of an action is exhibited. So far i've been reading a lot of the work done by psychophysiologists, and have been formulating a "map" per se of the brain.

I've run into a few problems though. I've tried contacting many of the labs who have published work, but no one ever responds to my questions about their work. Second, the university I am enrolled hasn't showed any interest in my work because there is no one who has any knowledge of current work done in the field of psychophysiology. So i've been stuck doing independent research at the moment. Anyone have any ideas on how I can show my work and get feedback as to whether or not my work has any potential?

You could post it here?
I can't promise a timely response but I'd read it.

Will do that. I have finals currently (I love how I have 5 finals in 2 days), but after tomorrow I will be working on transferring it from paper to computer.

i'd like to see your ideas, too, and will offer feedback