Textbook in PDF format

Machine Learning is an exciting topic with a myriad of applications. However, most textbooks are targeted towards Computer Science students. This, however, creates a complication for scientists across the physical sciences that also want to understand the main concepts of Machine Learning and look ahead to applications and advancements in their fields.
This textbook bridges this gap, providing an introduction to the mathematical foundations for the main algorithms used in Machine Learning for those from the physical sciences, without a formal background in Computer Science. It demonstrates how Machine Learning can be used to solve problems in physics and engineering, targeting senior undergraduate and graduate students in physics and electrical engineering, alongside advanced researchers.
Although this book is about Machine Learning, it does not aim at teaching students how to code and use libraries popularized in the computer science community. Although this book is about physics, it does not aim at teaching students how to solve particular problems in physics. The main goal was to translate many Machine Learning algorithms into a language that physicists can understand and use. To achieve this goal, a combination of discussions, mathematical formalism, and coding was used. The language chosen for the codes was Julia for two reasons: i) it is a very readable language that maps mathematics to code very clearly, and ii) the execution of its programs can be significantly faster than that of many other languages, and this is particularly necessary for solving problems in physics.
Key Features:
Includes detailed algorithms
Supplemented by codes in Julia: a high-performing language and one that is easy to read for those in the natural sciences
All algorithms are presented with a good mathematical background
SECTION I Foundations
Multivariate Calculus
Probability Theory
SECTION II Unsupervised Learning
Dimensionality Reduction
Cluster Analysis
Vector Quantization Techniques
SECTION III Supervised Learning
Regression Models
Classification
SECTION IV Neuronal-Inspired Learning
Feedforward Networks
Advanced Network Architectures
SECTION V Reinforcement Learning
Value Methods
Gradient Methods