1. Introduction1.1: The basic idea and history of Machine Learning1.2: Mathematical formulation of the basic learning problem1.3: Nonlinear regression in highdimensions1.4: Recent advancements1.5: No free lunchI A PRACTICAL GUIDE TO MACHINE LEARNING2. Scientific programming with Python2.1: Programming environment2.2: Basic language elements2.3: Code efficiency and vectorization2.4: Data handling2.5: Image processing and convolutional filters3. Machine learning with sklearn3.1: Classification with SVC, RFC and MLP3.2: Performance measures and evaluations3.3: Data handling3.4: Dimensionality reduction, feature selection, and tSN3.5: Decision Trees and Random Forests *3.6: Support Vector Machines (SVM) *4. Neural Networks and Keras4.1: Neurons and the threshold perceptron4.2: Multilayer Perceptron (MLP) and Keras4.3: Representational learning4.4: Convolutional Neural Networks (CNNs)4.5: What and Where4.6: More tricks of the tradeII FOUNDATIONS: REGRESSION AND PROBABILISTIC MODELING5. Regression and optimization5.1: Linear regression and gradient descent5.2: Error surface and challenges for gradient descent5.3: Advanced gradient optimization (learning)5.4: Regularization: Ridge regression and LASSO5.5: Nonlinear regression5.6: Backpropagation5.7: Automatic differentiation6. Basic probability theory6.1: Random numbers and their probability (density) function6.2: Moments: mean, variance, etc.6.3: Examples of probability (density) functions6.4: Some advanced concepts6.5: Density functions of multiple random variables6.6: How to combine prior knowledge with new evidence7. Probabilistic regression and Bayes nets7.1: Probabilistic models7.2: Learning in probabilistic models: Maximum likelihood estimate7.3: Probabilistic classification7.4: MAP and Regularization with priors7.5: Bayes Nets: Multivariate causal modeling7.6: Probabilistic and Stochastic Neural Networks8. Generative Models8.1: Modelling classes8.2: Supervised generative models8.3: Naive Bayes8.4: Unsupervised generative models8.5: Generative Neural NetworksIII ADVANCED LEARNING MODELS9. Cyclic Models and Recurrent Neural Networks9.1: Sequence processing9.2: Simple Sequence MLP and RNN in Keras9.3: Gated RNN and attention9.4: Models with symmetric lateral connections10. Reinforcement Learning10.1: Formalization of the problem setting10.2: Modelbased Reinforcement Learning10.3: Modelfree Reinforcement Learning10.4: Deep Reinforcement Learning10.5: Actors and actorcritics11. AI, the brain, and our society11.1: Different levels of modeling and the brain11.2: Machine learning and AI11.3: The impact machine learning technology on society

Machine learning is exploding, both in research and for industrial applications. This book aims to be a brief introduction to this area given the importance of this topic in many disciplines, from sciences to engineering, and even for its broader impact on our society. This book tries to contribute with a style that keeps a balance between brevity of explanations, the rigor of mathematical arguments, and outlining principle ideas. At the same time, this book tries to give some comprehensive overview of a variety of methods to see their relation on specialization within this area. This includes some introduction to Bayesian approaches to modeling as well as deep learning. Writing small programs to apply machine learning techniques is made easy today by the availability of high-level programming systems. This book offers examples in Python with the machine learning libraries sklearn and Keras. The first four chapters concentrate largely on the practical side of applying machine learning techniques. The book then discusses more fundamental concepts and includes their formulation in a probabilistic context. This is followed by chapters on advanced models, that of recurrent neural networks and that of reinforcement learning. The book closes with a brief discussion on the impact of machine learning and AI on our society.--