A Study on Neural Network Architectures

Abstract

With the growing emphasis on autonomy, intelligence and an increased amount of information required by businesses, traditional processing technology can only cope through faster hardware with more complex customized software.  The traditional computation techniques of programming were not capable enough to solve “hard” problems like pattern recognition, prediction, compression, optimization, classification and machine learning. In order to solve such problems, an interest towards developing intelligent computation systems became stronger. To develop such intelligent systems, innumerable advances have been made by the researchers.

An artificial neural network is a data processing system consisting of a huge number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. These artificial neurons are pigeonholed on the basis of architecture, training or learning method and activation function. The neural network architecture is the arrangement of neurons to form layers and connections scheme formed in between and within the layers. Neural network architectures are broadly classified into feed-forward and feedback architectures that further contain single and multiple layers. The feed-forward networks provide a unidirectional signal flow whereas in the feedback networks the signals can flow in both the directions. These neural network architectures are trained through various learning algorithms for producing most efficient solutions to computation problems. In this paper, we present neural network architectures that play a crucial role in modelling the intelligent systems.

Keywords: Artificial Neural Network, feed-forward networks, feedback networks .