CIS 421/521 - Artificial Intelligence
Fall 2017


Mitch Marcus
Levine 503, 215-898-2538
mitch (AT) standard local email address
Office Hours: TBA & by appointment
Teaching Assistants
See Piazza for schedule
Jack Carlson
carjack (AT) standard local email address
Heejin Jeong
heejinj (AT) standard local email address
Charlie Nickerson
chnick (AT) standard local email address
Eddie Smith
noes (AT) standard local email address
Kevin Wang
kevw (AT) standard local email address
Jiawei Xue
jiaweix (AT) standard local email address
Ming Zhang
mingzha (AT) standard local email address
Course Administrator
Cheryl Hickey
Levine 502, 215-898-3538
cherylh (AT) standard local email address

Class Schedule: Tuesday & Thursday noon-1:30 LEVINE 101 (Wu & Chen Auditorium)

Artificial Intelligence is considered from the point of view of a resource-limited knowledge-based agent who must reason and act in the world. Topics include search, knowledge representation and reasoning, probabilistic reasoning, machine learning, logic, automatic theorem proving, and natural language processing. Programming assignments in Python.

Prerequisites: Strong knowledge of programming and data structures required. Introductory statistics and logic will be useful.


Web Page:

Artificial Intelligence: A Modern Approach
(Third Edition) 2009
Stuart Russell and Peter Norvig
Prentice Hall Series in Artificial Intelligence

50% Homeworks
25% Midterm 1
25% Midterm 2
Homework will be due at 11:59 on specified dates. Each student is allowed to twice submit a homework late, by up to 48 hours late each time, with no penalty. Each student's lowest homework grade will be dropped when calculating the average homework grade at the end of semester. The only exception to this policy will be in times of dire need, by permission of Professor Marcus. Please do not stay silent if you are in dire need. If you submit a homework late but have already used your 2 extensions, you will get a 0 for that homework.
Academic Integrity:
We have strong expectations that students will follow Penn's Code of Academic Integrity. Academic dishonesty, as defined in the Code of Integrity, will not be tolerated. All violations will be referred to the Office of Student Conduct.

Back to Top


Links to copies classroom slides in PDF format will appear below.
Module 0: Introduction 
Module 1: Search (AIMA Textbook: Chapters 3-6)
  • Uninformed Search
    • 9/7 Search Problem Formulation  [(pdf)][(6up)] (AIMA 3.1-3.2)
    • 9/12 Uninformed Search   [(pdf)] [(6up)] (AIMA 3.3-3.4)
    • 9/14  NO CLASS
  • Informed Search
    • 9/19  Informed Search Part I [(pdf)] [(6up)] (AIMA 3.5.1-3.5.2)
    • 9/21  NO CLASS
    • 9/26   Informed Search Part II [(pdf)] [(6up)]
    • 9/28   Hill climbing, simulated annealing, genetic algorithms [(pdf)] [(6up)] (AIMA 3.6, 4.1)
  • Adversarial Search
    • 10/3  2-Player Games Part I [( pdf)] [( 6up)] (AIMA 5.1-5.2)
    • 10/5  NO CLASS - Fall Term Break!
    • 10/10   2-Player Games II: Alpha-Beta Pruning [( pdf)] [( 6up)] (AIMA 5.3)
  • Constraint Satisfaction
    • 10/12  Constraint Satisfaction [(pdf)] [(6-up)] (AIMA 6.1-6.4)

Module 2: Machine Learning and Natural Language Processing
  • Introduction to Probability
    • 10/17   Uncertainty & Probability [(pdf)] [(6-up)] (AIMA 13.1) (see Gallier's book excerpt below)
      A review of discrete probabiliity theory, excerpted from Prof. Jean Gallier's discrete mathematics textbook, can be found [here.]
    • 10/19  An AI-ish view of Probability, Conditional Probability, Bayes Theorem [(pdf)] [(6-up)]

A practice exam is available here and with answers here. This exam may vary in format from your exam, which will be largely multiple choice. Also, a couple of questions on this exam are not in the material we've covered. See Piazza for more details.

  • Naive Bayes & Spam Filtering
    • 10/24   Naive Bayes & Spam Filtering (AIMA 22.2)
  • Graphical Models: Bayesian Networks
    • 10/31   Bayes Nets & A little more on smoothing (AIMA 14.1-14.3)
  • Topics in Natural Language Processing and Human Language Technology
    • 11/2   Intro to NLP
    • Hidden Markov Models for Tagging and Speech Recognition
      • 11/7 & 11/14   Introduction to Markov Models
        (some topics covered in AIMA 15.2; Markov Models in Jurafsky & Martin, Speech and Language Processing, 4.1-4.3; Smoothing in J & M Chap. 4.5 Intro and 4.5.1)
      • 11/9   Part of Speech Tagging and Hidden Markov Models - Part 1
      • 11/16 & 11/21   Hidden Markov Models - Three Formal Problems
        (some topics covered in AIMA 15.3. Good discussion in J&M, 5.1, 5.2, 5.5
        You can download Rabiner&Juang 1986 from Citeseer through the Penn Library website - the slides follow this paper pretty closely.)
        (parallel treatment in AIMA 23.5)
      • 11/23 NO CLASS Thanksgiving
      • 11/28   Speech Recognition
    • Perceptrons and Support Vector Machines
      • 11/30   Perceptrons and Support Vector Machines
        (parallel to some topics covered in AIMA 18.1-2, 18.6.3, 18.9 Good discussion in J&M, 5.1, 5.2, 5.5)
Final Lectures
  • 12/5   The Singularity - A Critique
  • 12/7   AI: Future Concerns

  • Back to Top


    PDF Files require Adobe Acrobat Reader
    DOC Files require Microsoft Word or Open Office