Page 198 - DCAP208_Management Support Systems

Unit 11: Neural Networks

More or less resembling the structure of their counterparts, ANN are composed of Notes
interconnected, simple processing elements called artificial neurons.

An ANN model emulates a biological neural network. Neural computing actually uses a
very limited set of concepts from biological neural systems.
A neural network is composed of processing elements organized in different ways to
form the network’s structure.
Complex practical applications require one or more hidden layers between the input and
output neurons and a correspondingly large number of weights.

There are several effective neural network models and algorithms. Some of the most
common are backpropagation (or feedforward), associative memory, and the recurrent
network.
Learning algorithms specify the process by which a neural network learns the underlying
relationship between input and outputs, or just among the inputs.

Although the development process of ANN is similar to the structured design
methodologies of traditional computer-based information systems, some phases are
unique or have some unique aspects.

11.4 Keywords

ANN: An artificial neural network (ANN), often just called a “neural network” (NN), is a
mathematical model or computational model based on biological neural networks.

Backpropagation: The backpropagation learning algorithm is the standard way of implementing
supervised training of feedforward neural networks.
Connection Weights: Connection weights express the relative strength of the input data or the
many connections that transfer data from layer to layer.
Feedforward Neural Network: Feedforward neural networks are a class of models that show
promise in classification and forecasting problems.
Hidden Layer: A hidden layer is a layer of neurons that takes input from the previous layer and
converts those inputs into outputs for further processing.
Neurons: The human brain is composed of special cells called neurons.
Summation Weights: The summation function computes the weighted sums of all the input
elements entering each processing element.
Transformation Function: The transformation (transfer) function combines the inputs coming
into a neuron from other neurons/sources and then produces an output based on the choice of
the transfer function

11.5 Review Questions

1. Explain the concept of ANN.
2. Describe the following terms: neuron, axon and synapse.

3. How do weights function in an ANN? Discuss.
4. What is the role of inputs and outputs in neural networks?
5. Discuss the steps in developing a neural network.
6. Describe the Elements of ANN.

LOVELY PROFESSIONAL UNIVERSITY 191