Implementations and Applications of Machine Learning

Presents practical, useful applications of machine learning for practitioners, students, and researchers

Provides on hands-on tools for a variety of machine learning techniques

Covers clustering algorithms, swarm intelligence, deep learning, and power grid control

Autorentext

Saad Subair was born on the banks of the river Nile, a few kilometers away from the capital Khartoum He is a Professor of Bioinformatics and Computer Science at the College of Computer Studies, International University of Africa (IUA), Khartoum, Sudan. Prof. Subair obtained a BSc from the University of Khartoum, PGD, MSc (Computer Science) and PhD (Bioinformatics) from UTM, Malaysia, and an MSc in Genetics from UPM, Malaysia He is an author and/or contributing author to several books, articles, and scientific papers published in USA, Germany, Malaysia, India, and Arabia. He has been Keynote Speaker in numerous regional conferences. Prof. Subair is a member of scientific and academic committees in multiple universities in the Gulf region including Princess Nourah bint Abdulrahman University at Riyadh, KSA. Prof Subair has trained hundreds of students in the fields of machine learning and bioinformatics, and has supervised and/or advised several research students who have achieved further successes in the UK and USA.

Christopher P. Thron is Associate Professor of Mathematics at Texas A&M University of Central Texas. Previously he spent a dozen years in the semiconductor industry as a systems engineer for NEC, Motorola, Freescale, and NXP. Besides consulting for various companies, Dr. Thron has obtained 3 Fulbright visiting professor fellowships and 3 U.S. Air Force faculty fellowships. He has conducted workshops and seminars in mathematical/machine learning software in several countries in Africa, as well as for the U.S. Army's Operational Test Command. Dr. Thron's research focuses on mathematical and statistical modeling in multiple areas of industrial mathematics, including operations research, signal processing, epidemiology, public health, and physics. He holds nine U.S. patents, and has published over 30 peer-reviewed articles.

Inhalt

Introduction.- Part 1: Machine learning concepts, methods, and software tools.- Overview.- Classifying algorithms.- Support vector machines.- Bayes classifiers.- Decision trees.- Clustering algorithms.- k-means and variants.- Gaussian mixture.- Association rules.- Optimization algorithms.- Genetic algorithms.- Swarm intelligence.- Deep learning,- Convolutional neural networks (CNN).- Other deep learning schema.- Part 2: Applications with implementations.- Protein secondary structure prediction.- Mapping heart disease risk.- Surgical performance monitoring.- Power grid control.- Conclusion.