Machine Learning (ML)

YouTube search... ...Google search

• Learning Techniques

Core: four main types of learning problems in machine learning

• In-Context Learning (ICL) ... LLMs understand to encode learning algorithms implicitly during their training processes
• Supervised Learning
  • Deductive Inference | Wikipedia
• Unsupervised Learning
• Reinforcement Learning (RL)

Hybrid: drawing from unsupervised and supervised learning

• Semi-Supervised Learning
  • Inductive Learning | Wikipedia
  • Transductive Learning | Wikipedia
• Self-Supervised Learning
• Multi-Instance Learning | Wikipedia

Other Techniques:

• Deep Learning
• Transfer Learning a model trained on one task is re-purposed on a second related task
  • Text Transfer Learning
  • Image/Video Transfer Learning
• Few Shot Learning
• Ensemble Learning
• Multi-Task Learning (MTL)
• Apprenticeship Learning - Inverse Reinforcement Learning (IRL)
• Imitation Learning
• Simulated Environment Learning
• Lifelong Learning - Catastrophic Forgetting Challenge
• Neural Structured Learning (NSL)
• Meta-Learning
• Online Learning
• Human-in-the-Loop (HITL) Learning / Active Learning
• Decentralized: Federated & Distributed Learning

Machine learning (ML) is a field devoted to understanding and building methods that let machines "learn" – that is, methods that leverage data to improve computer performance on some set of tasks. It is seen as a broad subfield of artificial intelligence. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. - Machine learning | Wikipedia