Introduction to Machine Learning

Catalog description

The study of computer algorithms that improve automatically through experience and by the use of datasets. Involves computers learning from data provided so that they carry out certain tasks. Employs various approaches to teach computers to accomplish tasks using training data to improve algorithms for solving a problem. Commonly used in speech recognition, spell-checker, autonomous vehicles, effective web search, disease diagnoses, gaming and more. Covers the necessary theory, principles and algorithms for machine learning. Emphasizes principles behind machine learning problems such as classification, regression, clustering, and reinforcement learning. Implements and analyzes models such as linear models, kernel machines, neural networks, and graphical models for different applications. 54.00 hours lecture and 18.00 hours laboratory. (Letter grade or Pass/No Pass option)