CSE 150 - Spring 2017
Introduction to Artificial Intelligence:
Probabilistic Reasoning and Decision Making

Prof. Lawrence Saul

Administrivia Syllabus Piazza GradeSource CAPEs

Subject

This course will introduce students to the probabilistic and statistical models at the heart of modern artificial intelligence. Specific topics to be covered include: probabilistic methods for reasoning and decision-making under uncertainty; inference and learning in Bayesian networks; prediction and planning in Markov decision processes; applications to intelligent systems, speech and natural language processing, information retrieval, and robotics.

Prerequisites

This course is aimed very broadly at undergraduates in mathematics, science, and engineering. Prerequisites are elementary probability, linear algebra, and calculus, as well as basic programming ability in some high-level language such as C, Java, Matlab, R, or Python. (Programming assignments are completed in the language of the student's choice.) Students of all backgrounds are welcome.

Texts

The course will not closely follow a particular text. The following texts, though not required, may be useful as general references:
  1. K. Korb and A. Nicholson, Bayesian Artificial Intelligence.
  2. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach.
  3. R. Sutton and A. Barto, Reinforcement Learning: An Introduction.

Instructors

  1. Lecturer: Lawrence Saul (saulcs.ucsd.edu)

  2. Teaching assistants:
    Saicharan Duppati (sduppatieng.ucsd.edu)
    Shubham Gupta (shg061eng.ucsd.edu)
    Nivetha Thiruverahan (nthiruveeng.ucsd.edu)
    Zhen Zhai (zzhaieng.ucsd.edu)

  3. Tutors:
    Leon Cheung (ljcheungucsd.edu)
    Sara Farsi (safarsieng.ucsd.edu)
    Zhiwei Jia (zjiaucsd.edu)
    Justin Lizama (jnlizamaucsd.edu)

Meetings

  1. Lectures: Tue/Thu 8:00-9:20 pm, Center 101.

  2. Instructor office hour: Fri 10-11 am, EBU3B-3214.

  3. Discussion sections:
    Mon 4-5 pm, Center 115 (Zhen)
    Mon 7-8 pm, Pepper Canyon Hall 106 (Sai)
    Thu 7-8 pm, Center 115 (Shubham)
    Fri 12-1 pm, CSB 001 (Nivetha)

  4. TA office hours:
    Mon 10-11 am, EBU3B-4217 (Zhen)
    Mon 3-4 pm, EBU3B-B250a (Nivetha)
    Thu 12:30-1:30 pm, EBU3B-4217 (Shubham)
    Fri 3-4 pm, EBU3B-B260a (Saicharan)

  5. Tutoring hours:
    Mon 10 am-12 pm, dungeon (Leon)
    Tue 10-11 am, TBA (Sara)
    Wed 3:30-5:30 pm, TBA (Justin)
    Thu 9:30 am-12:30 pm, EBU3B-B250a (Zhiwei)
    Fri 2-3 pm, dungeon (Leon)
    Sat 10 am-12 pm, TBA (Sara)

  6. Final exam: Thu June 15, 8-11 am

Grading

  1. homework (30%) - best 6 of 7
  2. midterm exam (20%)
  3. final exam (50%)

Syllabus

Tue Apr 04Administrivia and course overview. 
Thu Apr 06Modeling uncertainty, review of probability. 
Tue Apr 11Examples of probabilistic reasoning.HW 1 out.
Thu Apr 13Belief networks: from probabilities to graphs. 
Tue Apr 18Conditional independence, d-separation.HW 1 due.
HW 2 out.
Thu Apr 20Inference in polytrees and loopy networks. 
Tue Apr 25Learning, maximum likelihood estimation.HW 2 due.
HW 3 out.
Thu Apr 27Naive Bayes and Markov models. 
Tue May 02Latent variable models, EM algorithm.HW 3 due.
HW 4 out.
Thu May 04Examples of EM algorithm. 
Tue May 09Hidden Markov models, speech recognition.HW 4 due.
Thu May 11Viterbi and forward-backward algorithms.
Belief updating.		 
Tue May 16Midterm exam HW 5 out.
Thu May 18Reinforcement learning. 
Tue May 23Markov decision processes.HW 5 due.
HW 6 out.
Thu May 25Policy evaluation, improvement, and iteration. 
Tue May 30Bellman optimality equation, value iteration.HW 6 due.
HW 7 out.
Thu Jun 01Temporal difference learning, Q-learning. 
Tue Jun 06TBA.HW 7 due.
Thu Jun 08TBA. 
Thu Jun 15Final exam