Publication Date

Spring 2014

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

Abstract

Machine learning is a branch of artificial intelligence in which the system is made to learn from data which can be used to make predictions, real world simulations, pattern recognitions and classifications of the input data. Among the various machine learning approaches in the sub-field of data classification, neural-network methods have been found to be an useful alternatives to the statistical techniques. An artificial neural network is a mathematical model, inspired by biological neural networks, are used for modeling complex relationships between inputs and outputs or to find patterns in data. The goal of the project is to construct a system capable of analyzing and predicting the output for the evaluation dataset provided by the "IBM Watson: The Great Mind Challenge" organized by IBM Research and "InnoCentive INSTINCT (Investigating Novel Statistical Techniques to Identify Neurophysiological Correlates of Trustworthiness) : The IARPA Trustworthiness Challenge" organized by the office of The Director Of National Intelligence. The objective of this paper is to understand the machine learning using neural networks. At the end of the paper, the comparison between different learning strategies have been shown which are used to increase the accuracy of the predictions. From the trained neural network up to a satisfactory level, we will be able to classify any generalized input, process often termed as generalization capability of the learning system.

Download

Share

COinS