یادگیری ماشین، یا، راهنمای غیررسمی برای دوره CS7641 دانشگاه جورجیا: یادگیری ماشین

Contents I Supervised Learning Techniques Classification Decision Trees Getting Answers Asking Questions: The ID3 Algorithm Considerations Ensemble Learning Bagging Boosting Support Vector Machines There are lines and there are lines... Support Vectors Extending SVMs: The Kernel Trick Summary Regression Linear Regression Neural Networks Perceptron Sigmoids Structure Biases Instance-Based Learning Nearest Neighbors Computational Learning Theory Learning to Learn: Interactions Space Complexity Version Spaces Error PAC Learning Epsilon Exhaustion Infinite Hypothesis Spaces Intuition Vapnik-Chervonenkis Dimension Information Theory Entropy: Information Certainty Joint Entropy: Mutual Information Kullback-Leibler Divergence Bayesian Learning Bayesian Learning Finding the Best Hypothesis Finding the Best Label Bayesian Inference Bayesian Networks Making Inferences Naïve Bayes II Unsupervised Learning Randomized Optimization Hill Climbing Simulated Annealing Genetic Algorithms High-Level Algorithm Cross-Over Challenges MIMIC High-Level Algorithm Estimating Distributions Practical Considerations Clustering Single Linkage Clustering Considerations k-Means Clustering Convergence Considerations Soft Clustering Expectation Maximization Considerations Analyzing Clustering Algorithms Properties How Many Clusters? Features Feature Selection Filtering Wrapping Describing Features Feature Transformation Motivation Principal Component Analysis Independent Component Analysis Alternatives III Reinforcement Learning Markov Decision Processes Bellman Equation Finding Policies Q-Learning Game Theory Games Relaxation: Non-Determinism Relaxation: Hidden Information Prisoner's Dilemma Nash Equilibrium Summary Uncertainty Tit-for-Tat Folk Theorem Pavlov's Strategy Coming Full Circle Example: Grid World Generalization Solving Stochastic Games Index of Terms