Homework_ _ Graduate AI Class Fall
COSC 4368 (Fall 2019)Review List Midterm1 Exam on Monday, March 4, 1:2:15pThe Midterm1 is scheduled for March 4 at 1p in our classroom. The exam will take 75 minutes and is open-books and notes and, but friends and other human beings are not permitted and, more importantly, the use of computers is not permitted!Relevant slide shows, pasted from the COSC 4368 Website that are relevant for the midterm exam:2019 Search Transparencies: Search1 (Classification of Search Problems, Terminology, and Overview ), Search2 (Problem Solving Agents), Search3 (Heuristic Search and Exploration), Search4 (Randomized Hill Climbing and Backtracking; not covered in textbook), Kamil on Backtracking and Mazes, Search5 (Games; Russel transparencies for Chapter 6; will cover transparencies 1-29, excluding those that cover games) Search5a (Brief Discussion of Bridge and Man vs. Machine Game Contests), Search6 (Russel slides Constraint Satisifaction Problems (CSP); we will cover slides 1-26, 32-37, and 41), 9), Search7 (to be dicussed briefly on February 18+20+27, 2019).2019 Teaching Material Evolutionary Computing (EC): EC1: Introduction to Evolutionary Computing and EC2:Example: Using EC to Solve Travelling Salesman Problems, Eiben-Smith Introduction to EC (they call 'EC': 'EA'; reading material) 2019 Game Theory Slides: G1: Introduction to Game Theory (Objectives, Game Normal forms, capability to compute NE for a simple game); Wikepidia page on Game Theory 2019 Machine Learning Transparencies: Reinforcement Learning: RL1 (Introduction to Reinforcement Learning), Remarks:The machine learning part of the exam centers on reinforcement learning basics (goals and objectives of RL, what is a policy, knowing what the learning and discount rate is, role of exploitation and exploration), Bellman Update, TD Learning (just focusing on learning the utility of states), but not on anything else (e.g. no SARSA and Q-learning). As far as the evolutionary computing is concerned only very basic questions will be asked in the exam, whereas more “deep” and more challenging questions will be asked about the search! As far as search is concerned, everything covered in the lecture mentioned above is relevant for the midterm.The “Introduction to AI” material we covered in the first week will be covered in the Final Exam, not Midterm1!Tentative Weights of 4 main topics in the midterm exam: Search 60-75%, Reinforcement Learning 15-20%, Evolutionary Computing: 10-15%, Game Theory 10% Relevant material from the Russel textbook (Third Edition):Chapter 3: pages 64-108; Chapter 4: 120-129 Chapter 5: 161-180 (the discussion of card games is not relevant), Chapter 6: 202-207, 214-218 Chapter 17: 645-656 Chapter 21: 830-831, 836-841.Material that was discussed in class that is relevant for the midterm exam (but not necessarily is discussed in the textbook):a) Simulated Annealing, traditional Hill Climbing and Randomized Hill Climbingb.)Read Eiben-Smith Introduction to EC (they call 'EC': 'EA') pages 15-24 and 32-34 and Wikipedia Game Theory Article. ................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- some major differences between expert systems and other
- cost sheet format
- education and certification com
- ucf computer science
- homework graduate ai class fall
- preliminary notes home digital technologies hub
- gerstein lab linkstream
- postgraduate progress report au
- papers university of wisconsin madison
- home scale up 360
Related searches
- homework vs no homework facts
- homework vs no homework statistics
- homework vs no homework article
- best ai investments for 2019
- ai stocks to buy 2019
- ai trace
- adobe ai tutorial
- ai vs machine learning vs deep learning
- ai vs machine learning
- difference ai and machine learning
- machine learning vs ai vs deep learning
- silicon valley ai companies list