- Artificial intelligence — Systems with ‘intelligent’ behavior. Could be based on logic, probabilistic reasoning, etc.
- Machine learning — Subset of AI that makes decisions based on mathematical models.
- Deep learning — Subset of machine learning, using deep neural networks.
Machine Learning can be divided into three sections:
- Supervised learning — There is input data and corresponding output data. Goal is to find features (patterns) to create predictions for unseen examples. Includes general neural networks, CNNs, Transformers, GNNs, etc.
- Unsupervised learning — There is input data but no corresponding output data or labels. Goals are diverse, ranging from generating new samples, revealing internal structures of datasets, etc. Includes GANs, Variational Autoencoders, Diffusion Models, etc.
- Reinforcement learning — Agents learn to perform actions in an environment with the goal of maximizing rewards in a non-deterministic way. Can be achieved using Markov Processes.
References
- Simon J. D. Prince — Understanding Deep Learning, Chapter One
This page is a part of Home.