Artificial Neural Network (ANN) - Overview

Artificial Neural Networks (ANNs) are modeled after the biological brain. ANNs are comprised of massively interconnected neurons. Neurons in an ANN are interconnected to each other with synapses of varying strengths. The synaptic strengths in ANN are also referred to as interconnection weights. 

Typically, neurons in ANN are arranged in layers. ANNs have an Input Layer, an Output Layer, and one or more Hidden Layers. Each Neuron in a layer connects to neurons in the next layer. 

Each Neurons receives inputs from other Neurons in the ANN. These inputs are summed up and the summed inputs go through a non-linear function producing a Neuron Output.

Training ANNs is equivalent to how the biological brain learns. Training is achieved by adapting or modifying the synaptic weight between each of the neurons in the ANN system.

Next page demonstrates how an ANN can me used to model and optimize a real process.