Methods Of Training In Artificial Neural Networks

Abstract

An artificial neural network is a system based on the operation of biological neural networks, in other words, is an emulation of biological neural system. It consists of a collection of interconnected neurons. From an engineering prospective, it can he regarded as an extension of the conventional data-processing technique. The following definition of neural networks may be offered as “A neural
network is a ‘massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use It resembles the brain in two respects: (1) knowledge is acquired by the network through a learning process, and (2) interneuron connection strengths known as synaptic weights are used to store the experiential knowledge. Recession prediction
has lately raised a great interest due to the recent world crisis events. In spite of the many advanced shallow computational methods that have extensively been proposed, most algorithms have not yet attained a desirable level of applicability. All show a good performance for a given financial setup but fail in general to create better and reliable models. The main focus of this paper is to present a learning model with strong ability to generate high level feature representations for accurate recession prediction.