BCT-DA-Component-Design-v7.docx



Tentative Teaching Plan COSC 6368 Fall 2016August 23+25: 1. Introduction to AI (covers chapter 1 in part and chapter 2) 2 lecturesAugust 29 September 1+8+13+15+20+22+27+29: 2. Problem Solving (covering chapter 3, 4 in part, 5, and 6 in part, centering on uninformed and informed search , adversarial search and games, A*, alpha-beta search, evolutionary computing, game theory (chapter 17 and other material), and constraint satisfaction problems, discussion course Project 1) 8.5 lecturesSeptember 29+October 4: 3. Planning and Acting (covering chapters 10 and 11 in part) 1.5 lecturesOctober 6+11+13+18+25+27 Nov. 1+3: 4. Machine Learning (covering learning from examples (chapter 18), deep learning (extra material) and reinforcement Learning (chapter 21, chapter17 in part; Discussion Course Project2) 8 lecturesOctober 20: Discussion of Homework1 and Review for Midterm ExamOctober 25: Midterm Exam November 8+10+15+17+22: 5. Reasoning and Learning in Uncertain Environments (covers chapters 13, 14, 15 in part, and 20 in part, centering on “basics” in probabilistic reasoning, na?ve Bayesian approaches, belief networks and hidden markov models (HMM)) 5 lecturesNovember 29: 6. Robotics (Chapter 25) 1 lectureDecember 1: 7. Course Summary, Discussion of Homework2 and Review for the Final Exam December 8, 2p: Final ExamAlgorithms Covered in COSC 63682. Problem Solving (covering chapter 3, 4 in part, 5, 6 in part and game theory (section 17.5)Graph SearchBread-first/Depth-first SearchUniform-cost SearchA*Maybe Recursive-best first search (RBFS)Hill Climbing Simulated AnnealingGenetic AlgorithmsMin-max algorithm with alpha-beta pruningBacktracking for CSP and other search problemsUsing Game Theory to determine the best strategy for 2-person games3. Planning and Acting (covering chapters 10 and 11 in part) Forward State-space SearchGraphPlan AlgorithmHierarchical Planning4. Machine Learning (covering learning from examples (chapter 18), deep learning (extra material) and reinforcement Learning (chapter 21, chapter17 in part)) Decision Tree Induction AlgorithmBackpropagation algorithm for multi-layer neural networksMaybe AdaBoost for ensemble learningMaybe some deep learning algorithm Value Iteration/Bellman Update to solve Bellman equations for utilities Policy IterationTemporal-Difference (TD) and Q-Learning5. Reasoning and Learning in Uncertain Environments (covers chapters 13, 14, 15 in part, and 20 in part)Inference using full-joint distributionsInference in Na?ve-Bayesian ApproachesInference with Belief NetworksHidden Markov Models—Learning and Inference ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download