CAP 5636 - Advanced Artificial Intelligence

Fall 2017

Class description: Principles of artificial intelligence. Uninformed and informed search. Constraint satisfaction. AI for game playing. Probabilistic reasoning, Markov decision processes, hidden Markov models, Bayes nets. Neural networks and deep learning.
Course objectives: By the end of the semester each student will be able to:
  • understand the search and decision making techniques used in modern artificial intelligence
  • apply artificial intelligence techniques in their own code
  • understand the societal and ethical implications of artificial intelligence
Instructor: Dr. Lotzi Bölöni
Office: HEC - 319
Phone: (407) 243-8256 (on last resort)
E-mail: (preferred means of communication)
Web Site:
The assignments and the other announcements will be posted on the course web site
Classroom: ENG2 203
Class Hours: Tue, Th 4:30PM - 5:45PM
Office Hours: Tue, Th 6:00PM - 7:30PM
Pre-requisites: The class does not depend on the undergraduate AI class, although some concepts might be easier if you have seen them before. The projects require Python programming. If you can program in any programming language (C/C++/Java/Javascript) you should be ok.
Required texts: There is no required textbook.
Recommended readings:
  • Stuart Russel and Peter Norvig, Artificial Intelligence - A Modern Approach, 3rd edition
  • Only full grades will be used based on the points obtained. A for 90 and above, B for 80-89, C for 70-79, F for lower than 70.
  • Points awarded: Midterm 1: 20 points, Midterm 2: 20 points, Homeworks/Projects: 30 points total, Final exam 30 points.
  • Some midterms, exams and homeworks will have bonus points, but no curve will be applied.
  • All the exams are open book, open notes. E-books on phones or tablets are acceptable (they must be in airplane mode). Laptops should not be used on exams.
  • Make up exams will be given only in justified cases.
Integrity: The department, college, and University are committed to honesty and integrity in all academic matters. We do not tolerate academic misconduct by students in any form, including cheating, plagiarism and commercial use of academic materials. Please consult the Golden Rule Handbook for the procedures which will be applied.
Verification of engagement: As of Fall 2014, all faculty members are required to document students' academic activity at the beginning of each course. In order to document that you began this course, please complete the following academic activity by the end of the first week of classes, or as soon as possible after adding the course, but no later than August 27. Failure to do so will result in a delay in the disbursement of your financial aid.
To satisfy this requirement, you must finish the first quiz posted online. Log in to Webcourses, choose CAP 5636, and submit your answers online.


Lecture Notes, Readings, Homeworks
Aug. 22
History and positioning of AI
[slides] History and positioning of AI
Aug. 24
Uninformed search
  • Reflex agents
  • Search problems
  • Depth first and breadth first search
  • Uniform cost search
[slides] Uninformed search
Aug. 29
Informed search: A* search and heuristics
  • Informed search methods
  • Heuristics
  • Greedy search
  • A* search
  • Graph search
[slides] Informed search
Homework 1: Project 1 from the Berkeley AI class. Due September 20th October 3rdOctober 10th
Points are worth as follows: Q1..Q4 25 points each, Q5..A8 10 points each. Total achievable points 140 points.
Aug. 31

Sept. 5

Mon, Sept. 7
UCF closed due to Hurricane Irma

Mon, Sept. 12
UCF closed due to Hurricane Irma

Mon, Sept. 14
UCF closed due to Hurricane Irma

Sept. 19
Game playing and adversarial search
  • Types of games
  • Adversarial search, minimax
  • The problem of depth
  • Evaluation functions
  • Alpha Beta pruning

[slides] Adversarial search
Sept. 21 Expectimax search and utilities
  • Expectimax search
  • Refresher about probabilities
  • Utilities and rationality
[slides] Expectimax search and utilities
Sept. 26
Markov decision processes 1
  • Defining MDPs: policies and utilities
  • Optimal policy, value of state, value of Q-state

[slides] Markov Decision Processes 1
Sept. 28
Markov decision processes 2
  • Policy iteration

[slides] Markov Decision Processes 2
Oct. 3
Reinforcement learning 1
  • Reinforcement learning as a twist on MDPs

[slides] Reinforcement learning 1
Oct. 5
  • Model-based and model-free learning
  • Temporal difference learning

Oct. 10
Reinforcement learning 2
  • Exploration vs. exploitation, regret
  • Generalization across states
  • Policy search

[slides] Reinforcement learning 2
Oct. 12
Midterm 1: from introduction to Markov Decision Processes (inclusive)
Oct. 17
  • Random variables
  • Joint and marginal distributions, conditional distribution

[slides] Probability
Oct. 19
  • Product rule, chain rule, Bayes' rule
  • Inference
  • Independence

Oct. 24
Markov models
  • Markov chains
  • Conditional independence
  • Stationary distributions

[slides] Markov models
Oct. 26
Hidden Markov models
  • Hidden Markov models
  • Example: robot localization

[slides] Hidden Markov models
Oct. 31

Homework 2: Project 3 from the Berkeley AI class. Due November 21st
Points are worth as follows: Q1..Q4 25 points each, Q5..A8 10 points each. Total achievable points: 140.
Nov. 2

Nov. 7

Nov. 9

Nov. 14
Midterm exam 2: From reinforcement learning to particle filters (inclusive)

Nov. 16
  • Most likely explanation
  • Speech recognition
Particle filters and applications of HMMs
  • Particle filters
  • Robot localization with particle filters
  • Dynamic Bayes nets

[slides] Particle filters and Applications of HMMs
Nov. 21
Classification, principles of machine learning, naive Bayes
  • Classification
  • Model-based classification
  • Naive Bayes
  • Spam filter example
  • Generalization and overfitting
  • Parameter estimation

[slides] Classification and naive Bayes
Nov. 23
Thanksgiving break

Nov. 28
-Classification and machine learning cont'd
[homework] Homework 3 - due December 7
Nov. 30
Artificial General Intelligence
  • General definitions of intelligence
  • Cognitive architectures
  • Can intelligence exist without embodiment?
  • Superintelligence

Final exam Thursday, December 07, 2017, 4:00 PM - 6:50 PM