ASCOT Library Zabali Campus

Includes bibliographical references and index.

1 Introduction p.1 --
2 Probabilistic Reasoning and Bioinformatics p.23 --
3 Information Entropy and Statistical Measures p.47 --
4 Ad Hoc, Ab Initio, and Bootstrap Signal Acquisition Methods p.77 --
5 Text Analytics p.125 --
6 Analysis of Sequential Data Using HMMs p.155 --
7 Generalized HMMs (GHMMs): Major Viterbi Variants p.207 --
8 Neuromanifolds and the Uniqueness of Relative Entropy p.235 --
9 Neural Net Learning and Loss Bounds Analysis p.253 --
10 Classification and Clustering p.279 --
11 Search Metaheuristics p.389 --
12 Stochastic Sequential Analysis (SSA) p.407 --
13 Deep Learning Tools – TensorFlow p.433 --
14 Nanopore Detection – A Case Study p.445 --
Appendix A: Python and Perl System Programming in Linux p.519 --
Appendix B: Physics p.529 --
Appendix C: Math p.531.

"This book provides an interdisciplinary presentation on machine learning, bioinformatics and statistics. This book is an accumulation of lecture notes and interesting research tidbits from over two decades of the author's teaching experience. The chapters in this book can be traversed in different ways for different course offerings. In the classroom, the trend is moving towards hands-on work with running code. Therefore, the author provides lots of sample code to explicitly explain and provide example-based code for various levels of project work. This book is especially useful for professionals entering the rapidly growing Machine Learning field due to its complete presentation of the mathematical underpinnings and extensive examples of programming implementations. Many Machine Learning (ML) textbooks miss a strong intro/basis in terms of information theory. Using mutual information alone, for example, a genome's encoding scheme can be 'cracked' with less than one page of Python code. On the implementation side, many ML professional/reference texts often do not shown how to actually access raw data files and reformat the data into some more usable form. Methods and implementations to do this are described in the proposed text, where most code examples are in Python (some in C/C++, Perl, and Java, as well). Once the data is in hand all sorts of fun analytics and advanced machine learning tools can be brought to bear."-- Provided by publisher