Introduction
This book is intended to be intense on theory and then create a bridge for practical programming. The standard topics like Probability theory, Calculus needed will dealt primarily in multivariate setting and univariate is used just for understanding.
Various ML algorithms, modelling techniques and Deep learning will be dealt primarily with strong theory so as reader can build foundations on research in this domain.
Programming is used in this book as an expression of theory and will be avoided where not necessary. However, this is extremely important and I believe if you get bold and assertive over theory, you will be much stronger in programming. Since the learning libraries and frameworks keep upgrading themselves, I feel it is helpful to make someone stronger in theory and facilitate towards good implementation rather than focus of current frameworks to teach or solve ML problems.