Feature learning, also known as representation learning, is a set of techniques in machine learning that enables a system to automatically discover the necessary representations for feature detection or classification from raw data. This eliminates the need for manual feature engineering and allows machines to learn and utilize these features for specific tasks. Feature learning can be done through supervised, unsupervised, or self-supervised methods.
Carnegie Mellon University
Spring 2018
A comprehensive exploration of machine learning theories and practical algorithms. Covers a broad spectrum of topics like decision tree learning, neural networks, statistical learning, and reinforcement learning. Encourages hands-on learning via programming assignments.
No concepts data
+ 55 more concepts