CIS 391 - Artificial Intelligence
Fall 2013


COURSE STRUCTURE
* MODULES AND NOTES * ASSIGNMENTS * RESOURCES

Instructor
Mitch Marcus
Levine 503, 215-898-2538
mitch (AT) cis.upen.edu (debug...)
Office Hours: Tuesday, 4:15-5:45 PM & by appointment (e-mail).

Course Administrator
Cheryl Hickey
Levine 502, 215-898-3538
cherylh (AT) cis.upen.edu
Teaching Assistants
Trisha Kothari
Location Levine 612
kotharit (AT) standard local email address
Office Hours: Tuesday, 7-8:30 PM

Menghan Li
Location Levine 512
menghanl (AT) standard local email address
Office Hours: Wednesday, 8-9:30 PM

Class Schedule:Tuesday & Thursday noon-1:30 PM, Levine 101

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: CIS 121

COURSE STRUCTURE


Web Page:
http://www.seas.upenn.edu/~cis391/

Textbook:
Artificial Intelligence: A Modern Approach
(Third Edition) 2009
Stuart Russell and Peter Norvig
Prentice Hall Series in Artificial Intelligence
Only the Third Edition, (Not International) will match the homeworks
Grading:
40% Homeworks (Final project will count for 1/4 of that amount)
30% Midterm 1
30% Midterm 2
Homework:
Homework will be due at noon on specified dates, unless otherwise specified
Late homeworks will be penalized unless an extension has been granted in advance :
-- 15% reduction if 0-24 hours late
-- 30% reduction if handed in at the following class
-- 45% reduction if handed in two classes later
-- no credit if more than a week late


Back to Top

CLASS MODULES


Links to classroom slides will appear below.

Lecture Notes are in PDF format.
Module 0: Introduction 
AIMA Textbook: Chapters 1-2
  • Introduction
    • 8/29   Introduction to Artificial Intelligence [(pdf) ][(6-up) ] ( AIMA, Chapter 2)
    • 9/3   Intelligent Agents [(pdf) ][(6-up) ] ( AIMA, Chapter 2)
    • 9/5   NO CLASS
  • Python Programming
    • Readings: Slides should be sufficient. See Resources for additional materials, including on-line Python library reference and on-line books.
    • 9/10  Python Review [(pdf)  ][(6up)  ]
        Much more thorough Python tutorial [(pdf)][(2up)]

Module 1: Search AIMA Textbook: Chapters 3-6
  • Uninformed Search
    • 9/12 Uninformed Search Part I [(pdf) ] [(6up) ] (AIMA 3.2-3.3)
    • 9/17 Uninformed Search Part II [(pdf) ] [(6up) ](AIMA 3.4)
  • Informed Search
    • 9/19  Informed Search Part I [(pdf) ] [(6up) ] (AIMA 3.5.1-3.5.2)
    • 9/24   Informed Search Part 1I [(pdf)] [(6up)] (AIMA 3.6, 4.1)
  • Adversarial Search
    • 9/26  2-Player Games: Adversarial Search [(pdf)][(6up)] (AIMA 5.1-5.4)
  • Constraint Satisfaction
    • 10/1  Interpreting Line Drawings via Constraint satisfaction [(pdf)] [(6-up)](AIMA 6.1(roughly), 6.2)
    • 10/1  Handout: The Huffman-Clowes Labelling Set [(pdf)]
    • 10/3 & 10/8  Introduction to Constraint Satisfaction [(pdf)] [(6-up)] (AIMA 6.1-6.4)

**NEW**: **MIDTERM 1: TUESDAY, October 29**

  • 10/24   Review slides [(pdf)][(6-up)]
  • A practice midterm with solutions is available here

Module 2: Machine Learning and Natural Language Processing
  • Introduction to Probability
    • 10/15  Uncertainty & Probability [(pdf)][(6-up)] (AIMA 13.1-13.5)
  • Naive Bayes & Spam Filtering
    • 10/17   Naive Bayes/Spam Filtering [(pdf)][(6-up)] (AIMA 22.2)
  • Graphical Models: Bayesian Networks & LDA
    • 10/22   Bayes Nets & LDA [(pdf) ] [(6-up) ] (AIMA 14.1-14.3)
  • 10/29 Midterm 1
  • Topics in Natural Language Processing and Human Language Technology
    • 10/31   Intro to NLP [(pdf)] [(6-up)]
    • Markov Models for Language Modeling, Hidden Markov Models for Tagging and Speech Recognition
      • 11/5   Language models and Markov Models [(pdf)][(6-up)]
        (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)
      • 11/7   Part of Speech Tagging and Hidden Markov Models [(pdf)][(6-up)]
        (some topics covered in AIMA 15.3. Good discussion in J&M, 5.1, 5.2, 5.5)
      • 11/14   Speech Recognition [(pdf)][(6-up)] (parallel treatment in AIMA 23.5)
    • 11/21   Perceptrons and Support Vector Machines [(pdf)][(6-up)]
      (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)

Module 3: Knowledge Representation and Logic


MIDTERM 2 - Wednesday, December 18, 12p.m.-2 Place: LRSM AUD, LRSM 112B

  • A practice midterm with solutions is available here.
  • Slides from midterm review session: [(pdf)][(6-up)]


Back to Top

HOMEWORK ASSIGNMENTS

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

Homework submission instructions can be found here

  • Homework 1 - **MODIFIED**: Due Thursday, September 26, 2013 by noon. Homework submission instructions can be found here .
    You can find the encrypted file vfd.txt for Problem 8 here. (Right click and then use "Save Link As..." or "Save Target As.." to save it...)

  • Homework 2 - Due Thursday, October 10, at noon.
    The code for the last question can be found here.

  • Homework 3 - Due Thursday, October 31, at noon.
    The sudoku problems to test on can be found here.

  • Homework 4 - Due Thursday, November 21, at noon..
    A tokenized version of Jane Austen's Pride and Prejudice can be found here.
    The Project Gutenberg original text can be found here.

  • Homework 5 - Due Thursday, December 5, at noon.
    The code for this problem can be found here and the dataset can be found here.

  • FINAL VERSION OF HOMEWORK 6: Homework 6 - Due Thursday, December 19, 11:59 p.m.. This version includes detailed instructions on using the new autograding code framework.
    The dataset can be found here.
    The new code framework, allowing for autograding, can be found here.


Back to Top

OTHER RESOURCES

Python Resources

Textbook Resources

Website for: Artificial Intelligence: A Modern Approach
(http://aima.cs.berkeley.edu/)
 


Back to Top


For more information, please contact mitch (AT) cis.upenn.edu