CIS 391 - Artificial Intelligence
Fall 2015
LECTURE SCHEDULE AND HANDOUTS * ASSIGNMENTS * RESOURCES
Instructors |
Mitch Marcus
Levine 503, 215-898-2538
mitch (AT) standard local email address
Office Hours: See Piazza for regular schedule & by appointment
|
Teaching Assistants |
Daniel Moroz
dmoroz (AT) standard local email address
Office Hours: See Piazza for schedule
|
Toma Pigli
tpigli (AT) standard local email address
Office Hours: See Piazza for schedule
|
Course Administrator |
Cheryl Hickey
Levine 502, 215-898-3538
cherylh (AT) standard local email address
|
Class Schedule: Tuesday & Thursday noon-1:30 Wu & Chen Auditorium (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 120, 121. Introductory statistics, introductory logic, and familiarity with finite state automata are all useful.
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:
- 50% Homeworks
- 25% Midterm 1
- 25% Midterm 2
- Homework:
- Homework will be due at 11:59 on specified dates with submission cut off
promptly. You can submit up to two homeworks late, but extensions after that will be granted
only for true emergencies. Your lowest homework grade will be dropped.
Please note that we insist that students
follow Penn's Code
of Academic Integrity, and that academic dishonesty, as defined in the Code of Integrity will
not be tolerated, and penalties will be severe.
Back to
Top
Links to classroom slides will appear below.
Lecture Notes are in PDF format.
Module 0: Introduction (AIMA Textbook: Chapters 1-2)
- Introduction
- 8/27 Introduction to Artificial Intelligence
[(pdf) ][(6-up) ] (AIMA, Chapters 1,2)
- Python Programming
- Readings: Slides should be sufficient. See Resources for
additional materials, including on-line Python library reference and on-line books.
- 9/1 Python Overview 1
[(pdf) ]
[(6up) ]
- 9/3 Python Overview 2
[(pdf) ]
[(6up) ]
Thorough Python tutorial
[(pdf)][(6up)]
Module 1: Search (AIMA Textbook: Chapters 3-6)
- Uninformed Search
- 9/8 Search Problem Formulation [(pdf) ]
[(6up) ]
(AIMA 3.1-3.3)
- 9/10 Uninformed Search [(pdf) ]
[(6up) ] (AIMA 3.4)
- 9/15 NO CLASS
- Informed Search
- 9/17 Informed Search Part I [(pdf) ]
[(6up) ] (AIMA 3.5.1-3.5.2)
- 9/22 Informed Search Part II: Hill climbing, simulated annealing, genetic algorithms
[(pdf)]
[(6up)] [(pptx)] (AIMA 3.6, 4.1)
- Adversarial Search
- Constraint Satisfaction
- 10/1 & 10/6 Introduction to Constraint Satisfaction [(pdf)]
[(6-up)] (AIMA 6.1-6.4)
- 10/8 FALL BREAK
- A practice exam with solutions is available here
This exam may vary in format from your exam.
Module 2: Machine Learning and Natural Language Processing
- Introduction to Probability
- 10/13 Uncertainty & Probability [(pdf)]
[(6-up)] (AIMA 13.1-13.5)
A review of discrete probabiliity theory, excerpted from Prof. Jean Gallier's discrete
mathematics textbook, can be found [here.]
- Conditional Probabilities, Naive Bayes & Spam Filtering
- 10/15 Bayes Rule & Naive Bayes [(pdf)][(6-up)] (AIMA 22.2)
- 10/22 Naive Bayes & Spam Filtering [(pdf)][(6-up)] AIMA 22.2)
- Graphical Models: Bayesian Networks & LDA
- 10/27 Bayes Nets & LDA [(pdf) ]
[(6-up) ] (AIMA 14.1-14.3)
- Topics in Natural Language Processing and Human Language Technology
- 10/29 Intro to NLP [(pdf)]
[(6-up)]
- Hidden Markov Models for Tagging and Speech Recognition
- 11/3 Introduction to Markov Models (revised)
[(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)
- 11/5 Part of Speech Tagging and Hidden Markov Models - Part 1
[(pdf)][(6-up)]
- 11/10 Hidden Markov Models - Three Formal Problems
[(pdf)][(6-up)]
(some topics covered in AIMA 15.3. Good discussion in J&M, 5.1, 5.2, 5.5)
- 11/12 Speech Recognition
[(pdf)][(6-up)]
(parallel treatment in AIMA 23.5)
- Perceptrons and Support Vector Machines
- 11/17 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)
MiniModule 3: Knowledge Representation and Logic
- Propositional Logic & Inference
- 11/19 Logical Agents, Introduction to Logic & Propositional Logic
[(pdf)][(6-up)] (AIMA 7.1-7.4)
- 11/24 & 12/1 Propositional Inference
[(pdf)][(6-up)] (AIMA 7.1-7.4)
- 11/26 Thanksgiving
- Final Lecture
UPDATE: MIDTERM 2 WILL BE HELD DURING THE LAST CLASS, TUESDAY, DECEMBER 8
A practice midterm with solutions is available here.
Back to Top
PDF Files require Adobe
Acrobat Reader DOC Files require Microsoft Word or Open
Office
- Homework 1
Due by 11:59 pm on Thursday, September 10, 2015.
Additional files: skeleton file.
- Homework 2
Due by 11:59 pm on Tuesday, September 22, 2015.
Additional files: skeleton file,
Lights Out GUI.
- Homework 3
Due by 11:59 pm on Tuesday, Oct 6, 2015.
Additional files: skeleton file,
Tile Puzzle GUI,
Grid Navigation GUI,
simple scene,
barrier scene,
random 50x50 scene,
Dominoes Game GUI.
- Homework 4
Due by 11:59 pm on Thursday, October 15, 2015.
Additional files: skeleton file,
test puzzles,
test puzzle solutions.
- Homework 5
Due by 11:59 pm on Thursday, October 29, 2015.
Additional files: skeleton file,
training and development data.
- Homework 6
Due by 11:59 pm on Thursday, November 5, 2015.
Additional files: skeleton file,
training and development data (same as previous homework).
- Homework 7
Due by 11:59 pm on Thursday, November 12, 2015
Additional files: skeleton file,
Frankenstein.
- Homework 8
Due by 11:59 pm on Thursday, November 19, 2015
Additional files: skeleton file,
Brown corpus.
- Homework 9
Due by 11:59 pm on Tuesday, December 1, 2015
Additional files: skeleton file,
data sets.
Back to Top
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