1. Machines
1.1. Classic
1.2. Adaptative
2. types of ML
2.1. UNsupervised Learning
2.1.1. Object segmentation (for example, users, products, movies, songs, and so on)
2.1.2. Similarity detection
2.1.3. Automatic labeling
2.2. supervised learning
2.2.1. Predictive analysis based on regression or categorical classification
2.2.2. Spam detection
2.2.3. Pattern detection
2.2.4. Natural Language Processing
2.2.5. Sentiment analysis
2.2.6. Automatic image classification
2.2.7. Automatic sequence processing (for example, music or speech)
2.3. Reinforcement LEarning
2.3.1. Reinforcement learning is particularly efficient when the environment is not completely deterministic, when it's often very dynamic, and when it's impossible to have a precise error measure. During the last few years, many classical algorithms have been applied to deep neural networks to learn the best policy for playing Atari video games and to teach an agent how to associate the right action with an input representing the state (usually a screenshot or a memory dump).
2.4. Deep Learning
2.4.1. Image classification
2.4.2. Real-time visual tracking
2.4.3. Autonomous car driving
2.4.4. Logistic optimization
2.4.5. Bioinformatics
2.4.6. Speech recognition