Machine Learning Handbook: Theory, Algorithms, and Implementation

by Giridhar Boray

.Machine Learning (ML) is an integral part of Artificial Intelligence which is finding increasing applications such as autonomous driving, speech recognition, recommendation systems, population prediction etc. The explosive growth in Machine Learning is due to almost simultaneous availability of high processing power, high storage capacity and high network speed. There are many excellent books on Machine Learning which provide excellent theoretical treatment. There is extensive library of routines (mostly in python) that one can use to quickly implement modern machine learning algorithms. This book attempts to provide a bridge between theoretical formulations of machine learning algorithms and implementation so that a practitioner can appreciate the theoretical underpinnings and develop the skills to modify or develop python routines from scratch instead of relying on built in routines always. This book attempts to cover 13 major machine learning algorithms - Linear Regression Learning, Logistic Regression Learning, k-Nearest Neighbour (k-NN) classification, Bayesian Learning, Decision Tree Learning, Random Forest Classifier, Principal Component Analysis, Artificial Neural Network Learning, k-Means Clustering, Reinforcement Learning, Support Vector Machines, Time Series Machine Learning, and Machine Learning with Adaptive Filters. These algorithms are implemented using commonly available tools such as Microsoft Excel and python. While many libraries and routine are available in implementing ML with languages such as Python, it is important for a practitioner to understand the basic theory behind the algorithms. This will enable one to develop customized solutions or modify available routines for specific problems or implement brand new algorithms for which there may not be ready made libraries or routines.

164 pages, Kindle Edition

Published March 21, 2023