Question

7. Explain the characteristics of a problem could be solved by using Neural Network.

Answer 1

Any Neural Network, irrespective of the style and logic of implementation has a few basic characteristics. These are mentioned below.

• An Artificial Neural Network (ANN) consists of large number of “neuron” like processing elements.
• All these processing elements have a large number of weighted connections between them.
• The connections between the elements provide a distributed representation of data.
• A Learning Process is implemented to acquire knowledge.

Keeping the above characteristics in mind, we can derive the basic elements of any Artificial Neural Network as follows:

• Processing Elements
• Topology
• Learning Algorithm

Processing Elements: As the ANN is a simplified computational model of a biological neural network, an ANN consists of basic processing units or elements similar to that of neurons of a brain.In general, a processing unit is made up of summing unit followed by an output unit. The function of a summing unit is to take multiple input values, weight each input value and calculate the weighted sum of those values.Based on the sign of the weight of each input, it is determined whether the input has a positive weight or a negative weight. The weighted sum of the summing unit is known as Activation Value and based on the signal from this activation value, the output is produced.Both the input and output can be either continuous or discrete as well as they can be either deterministic or fuzzy.

Topology: Any Artificial Neural Network will become useful only when all the processing elements are organized in an appropriate manner so that they can accomplish the task of pattern recognition.This organization or arrangement of the processing elements, their interconnections, inputs and outputs is simply known as Topology. Generally, in an ANN, the processing units are arranged into layers and all the units in a particular layer have the same activation values and output values. Connection can be made between layers in multiple ways like processing unit of one layer connected to a unit of another layer, processing unit of a layer connected to a unit of same layer, etc

Learning Algorithm:The final and important elements of any ANN are Learning Algorithms or Laws. The operation any neural network is governed by Neural Dynamics consisting of both activation state dynamics and synaptic weight dynamics.Learning Algorithms or Laws are implementations of synaptic dynamics and are described in terms of first derivative of the weights. These leaning laws can be supervised, unsupervised or a hybrid of both.