---------------------------------------------------------
Human being is a densely interconnected network of approximately 10 "neurons", each connected to, an average,10^4 others.
Neuron activity is excited or inhibited through connections to other neurons. The fasted neuron switching time are known to be on the order of 10^-3 seconds.
Signals can be transmitted unchanged or they can be altered by synapses. A synapse is able to increase or decrease the strength of the connection from the neuron to neuron and cause excitation or inhibition of a subsequence neuron. This is where information is stored.
The information processing abilities of biological neural systems must follow from highly parallel processes operating on representations that are distributed over many neurons.
One motivation for ANN is to capture this kind of highly parallel computation based on distributed representations.
Neural Network Representation
---------------------------------------------------------
An ANN is composed of processing elements called or perceptrons, organized in different ways to form the networks structure.
*Processing Elements
---------------------------------------------
An ANN consists of perceptrons. Each of the perceptrons receives inputs, processes inputs and delivers a single output. The input can be raw input data or the output of other perceptrons. The output can be the final result or it can be inputs to other perceptrons.
*The Network
---------------------------------------------
Each ANN is composed of a collection of perceptrons grouped in layers. A typical structure (3 layers)input, the hidden layer and output.Several hidden layers can be placed between the input and output layers.
Appropriate Problems for Neural Network
------------------------------------------------------------------------------------
*ANN learning is well suited to problems in which the training data corresponds to noisy, complex sensor data. It is also applicable to problems for which more symbolic representations are used.
*The backpropagation (BP) algorithm is the most commonly used ANN learning technique.
Examples
--------------------------------------
- Speech Recognition
- Image Classification
- Financial Prediction
Perceptons
---------------------------------
A perceptron takes a sector of real-valued inputs, calculate a linear combitnations of these inputs, then outputs.
*a 1 of the result is > some threshold
*a -1 otherwise
Given real-valued input X1 throught Xn, the output O(X1,...,Xn) computed by the perceptron is
O(X1,............,Xn) = 1 if W0 + W1X1 + .............. + WnXn) > 0
-1 otherwise
where Wi is a real-valued constant or weight
* Notice the quantity (-W0) is a threshold that the weighted combination of inputs W1X1 + .......... + WnXn must surpass in order of perceptron to output a 1.
