Overview of Machine Learning

Abstract

The field of machine learning is introduced at a high level of abstraction. The concepts of supervised and unsupervised learning, regression, and classification are all discussed. A major guiding notion of learning is the balance between bias, variance, and model complexity. The neural network (feed-forward and recurrent), support vector machine, random forest, self-organizing map, and Bayesian network are all examples of models that machine learning can develop. The core ideas of partitioning a dataset into training, testing, and validation sets, as well as performing cross-validation, are addressed next. The importance of the domain expert in keeping the project real is discussed next, followed by evaluating the model's goodness. The chapter ends with some practical advice on how to perform a machine learning project.