BASICS OF ARTIFICIAL NEURAL NETWORK

Abstract

An Artificial Neural Network (ANN) is a typical model in machine learning that is inspired by the structure and function of the human brain. Its purpose is to imitate the functioning of human brain to solve complex problems. It is made up of three layers: input layer, hidden layer and output layer. ANN model output is dependent on some parameters that are, input, weights, summation function and activation function. ANN uses a training algorithm that is back propagation algorithm to learn the datasets. The main concept behind ANNs is to imitate the processing of information and learning from it the way human brain does. ANN is applied in image recognition, speech recognition and medical diagnosis. This paper gives the overview of Artificial Neural Network, Its architecture types, working, algorithms used and its pros & cons. It also explains how actually ANN works with the help of an example.