24. Overview of Part IV: Machine learning basics#
Machine learning (ML) is the study of computer algorithms that can improve automatically through experience and by the use of data. … A subset of machine learning is closely related to computational statistics, which focuses on making predictions using computers; but not all machine learning is statistical learning. … Machine learning and statistics are closely related fields in terms of methods, but distinct in their principal goal: statistics draws population inferences from a sample, while machine learning finds generalizable predictive patterns.
—Wikipedia article on Machine Learning
Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.
—Ed Burns, TechTarget
We will be selective in our coverage, focusing on aspects that will ultimately connect to our Bayesian perspective. The chapters here are:
Machine learning: Overview gives a general overview of machine learning: types of learning, data handling and ethical aspects, model validation, and data bias and fairness.
Logistic Regression introduces binary and multi-class classification, with first machine-learning examples.
Artificial neural networks covers the architecture of artificial neural networks (ANNs), the mathematical model of feed-forward networks, and training with back-propagation, with PyTorch demonstration notebooks.
*Convolutional neural networks (or CNNs) are networks designed for image data.
A non-empirical, field-theory-based treatment of ANNs that expands around the large-width limit is presented in Part V, see ANNs in the large-width limit.