Machine learning divides into unsupervised, supervised, and reinforcement learning

Evidence

The field of machine learning comprises three major areas: In unsupervised learning, a machine is simply given a heap of data and—as with the word2vec system—told to make sense of it, to find patterns, regularities, useful ways of condensing or representing or visualizing it. In supervised learning, the system is given a series of categorized or labeled examples—like parolees who went on to be rearrested and others who did not—and told to make predictions about new examples it hasn’t seen yet, or for which the ground truth is not yet known. And in reinforcement learning, the system is placed into an environment with rewards and punishments—like the boat-racing track with power-ups and hazards—and told to figure out the best way to minimize the punishments and maximize the rewards. — Brian Christian, The Alignment Problem, 58

Categorization

• DEFINE: A crisp conceptual framework distinguishing the three branches of machine learning, useful as a permanent reference.
• corroborated: 2 independent passages support this claim — Brian Christian, The Alignment Problem, 58
• XREF: connects to: Complex behavior emerges from rewarding successive small approximations — Brian Christian, The Alignment Problem, 660; ImageNet’s three million human-labeled images enabled the deep learning breakthrough — Brian Christian, The Alignment Problem, 99; Machine learning underlies Big Data and drives today’s massive investment. — Nick Couldry & Ulises A. Mejias, The Costs of Connection: How Data Is…, 392 (+2 more)

Related

• ImageNet’s three million human-labeled images enabled the deep learning breakthrough (similarity 0.80)
• Reinforcement-learning lets algorithms reprogram themselves using internal performance and reward subroutines. (similarity 0.79)

Broader Connections

• Complex behavior emerges from rewarding successive small approximations #exemplifies (0.75) — Brian Christian, The Alignment Problem, 660
• ImageNet’s three million human-labeled images enabled the deep learning breakthrough #exemplifies (0.65) — Brian Christian, The Alignment Problem, 99