v
Current announcements will appear here,
at top-level, for quick and easy inspection.
The
course is based on, and the UCI bookstore has, the 3rd edition. The assigned
textbook reading is required, and is fair game for quizzes and exams. You
place yourself at a distinct disadvantage if you do not have the textbook. I expect that you have a personal copy
of the textbook, and quizzes and exams are written accordingly.
Please
purchase or rent your own personal textbook for the quarter (and then resell it
back to the UCI Bookstore at the end if you don't want it for reference).
Please do not
jeopardize your precious educational experience with the false economy of trying
to save a few dollars by not having a personal copy of the textbook.
Also,
for your convenience, I have requested that a copy of the textbook be placed on
reserve in the UCI Science Library. There is a two-hour check-out limit. However,
please understand that with high student enrollments, it is unrealistic to
expect that these thin reserves always will be available when you need
them. Please
purchase or rent your own personal textbook. Otherwise, you are at a severe
disadvantage.
I do deplore the high cost of modern
textbooks. You may find the
textbook cheaper if you look online at sites such as eBay.com, Amazon.com,
etc.; or search the web for other sites related to the textbook.
Pierre Baldi:
Baldi, et al., 2014, “Deep
Learning in High-Energy Physics: Improving the Search for Exotic
Particles”
Baldi & Sadowsk, 2016, “A
Theory of Local Learning, the Learning Channel, and the Optimality of
Backpropagation”
Rina Dechter:
Dechter & Pearl, 1985, “Generalized
Best-First Search Strategies and the Optimality of A*”
Dechter, et al., 1991, “Temporal
Constraint Networks”
Charless Fowlkes:
Yang,
et al., 2011, “Layered
Object Models for Image Segmentation”
Hallman
& Fowlkes, 2015, “Oriented
Edge Forests for Boundary Detection” (Sam Hallman was a UCI undergraduate when he presented
this paper as a talk at the Computer
Vision and Pattern Recognition conference. Sam completed his PhD with me in
2015. He is now working at Amazon.
--- From Charless Fowlkes)
Diaz,
et al., 2016, “Lifting
GIS Maps into Strong Geometric Context” (This paper uses a dataset of photos
taken on the UCI campus and a 3D model of our corner of campus. --- From Charless Fowlkes)
Ren,
et al., 2008, “Learning
Probabilistic Models for Contour Completion in Natural Images” (This is an older paper from my
PhD but has a very nice connection to the discussion of Huffman & Clowes line labeling as constraint satisfaction in Russell
& Norvig, AIMA, Chap 24, 2nd ed. --- From Charless Fowlkes)
Alexander Ihler:
TBA
(pending).
Richard Lathrop:
Lathrop, et al., 1999, “Knowledge-based Avoidance of Drug-Resistant HIV Mutants” (Miriam Raphael and Sophia Deeds-Rubin were ICS undergraduate women when they shared the cover illustration of AI Magazine and an award from the Innovative Applications of Artificial Intelligence conference for this paper. --- From Richard Lathrop)
Danziger, et al., 2009, “Predicting Positive p53 Cancer Rescue Regions Using Most Informative Positive (MIP) Active Learning”
Wassman, et al., 2013, “Computational
Identification of a Transiently Open L1/S3 Pocket for Reactivation of Mutant
p53”
Eric Mjolsness:
Mjolsness, 2013, “Quantitative
Symbolic Process Models: How a Fair Fraction of Intelligence Could be Abstracted in AI Research”
Mjolsness & Cunha, 2012, “Topological
object types for morphodynamic modeling
languages”
Mjolsness, 2010, “Towards
Measurable Types for Dynamical Process Modeling Languages”
Hernando Ombao:
Wang,
et al., 2016, “Modeling
Effective Connectivity in High-Dimensional Cortical Source Signals”
Donald Patterson:
Patterson,
et al., 2003, “Inferring High-Level
Behavior from Low-Level Sensors” (This paper won a Ten-Year
Impact Award. --- From Donald Patterson)
Patterson,
et al., 2004, “Opportunity Knocks: A
System to Provide Cognitive Assistance with Transportation Services”
Babak Shahbaba:
Shahbaba & Neal, 2009, “Nonlinear Models
Using Dirichlet Process Mixtures”
Lan, et al., 2014, “Wormhole
Hamiltonian Monte Carlo”
Sameer Singh:
Ribeiro,
et al., 2016, “ ‘Why Should I Trust You?’ Explaining the
Predictions of Any Classifier” (This paper won the Audience Appreciation Award at the
ACM SIG Conference on Knowledge Discovery and Data Mining (KDD); see easy
to read article by us on O'Reilly; view Summary Video. --- From
Sameer Singh)
Gupta
& Singh, 2016, “Collective
Factorization for Relational Data: An Evaluation on the Yelp Datasets”
(Nitish
Gupta was an undergraduate who shared in the publication of this work, which was
a grand prize winner in Round 4 of the Yelp dataset challenge. ---
From Sameer Singh)
Padraic Smyth:
Gaffney,
et al., 2007, “Probabilistic
clustering of extratropical cyclones using regression mixture models”
(The key student involved
in this work started out as an ICS undergraduate. Scott Gaffney took ICS 171
and 175, got interested in AI, started to work in my group, decided to stay in
ICS for his PhD, did a terrific job in writing a thesis on curve-clustering and
working with collaborators in climate science to apply it to important
scientific problems, and is now one of the leaders of Yahoo! Labs reporting
directly to the CEO there. Scott grew up locally in Orange County and is
someone I like to point as a great success story for ICS. --- From Padhraic Smyth)
Hal Stern:
Heins & Stern, 2014, “A Statistical
Model for Event Sequence Data”
Xiaohui Xie:
Kim
& Xie, 2014, “Handwritten
Hangul recognition using deep convolutional neural networks”
The following represents a preliminary syllabus. Some changes in the
lecture sequence may occur due to earthquakes, fires, floods, wars, natural
disasters, unnatural disasters, or the discretion of the instructor based on
class progress.
Background Reading and Lecture Slides will be changed or revised as the
class progresses at the discretion of the instructor. Please note: I often tweak or revise the lecture
slides prior to or after the lecture; please ensure that you have the current
version.
Please read the assigned textbook reading and review the lecture notes in advance of each lecture, then again after each lecture.
Week
|
Date
|
Event
|
Lecture
Topic
|
Lecture
Reading
|
1
|
Thu 22 Sep
|
Lecture
|
Class setup, Intro Agents
|
Chapters 1-2
|
|
Fri 23 Sep
|
Discussion Section
|
Review, questions
|
|
2
|
Mon 26 Sep
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 27 Sep
|
Lecture
|
Intro State Space Search
Uninformed
Search
|
Chapter 3.1-3.4 |
|
|
Wed 28 Sep
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 29 Sep
|
Lecture
|
Heuristic Search
|
Chapter 3.5-3.7
|
|
Fri 30 Sep
|
Discussion Section
|
Review, questions
|
|
|
Sun 2 Oct
|
Team
formation deadline
|
You must register your team name (yourself alone, or a team of at most
two people).
|
|
3
|
Mon 3 Oct
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 4 Oct
|
Lecture
|
Local Search
|
Chapter 4.1-4.2
|
|
|
Wed 5 Oct
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 6 Oct
|
Quiz
#1
Lecture
|
Game (Adversarial) Search A
|
Chapter 5.1, 5.2, 5.4
|
|
Fri 7 Oct
|
Discussion Section
|
Review, questions
|
|
|
Sun 9 Oct
|
Minimal
AI deadline
|
Minimal AI must run on
openlab.ics.uci.edu in the tournament shell and at least make a random move
on its turn
|
|
4
|
Mon 10 Oct
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 11 Oct
|
Lecture
|
Game (Adversarial) Search B
|
Chapter 5.3 (optional: 5.5+) |
|
|
Wed 12 Oct
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 13 Oct
|
Lecture
|
Constraint Satisfaction A
|
Chapter 6.1-6.4, except 6.3.3
|
|
Fri 14 Oct
|
Discussion Section
|
Review, questions
|
|
5
|
Mon 17 Oct
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 18 Oct
|
Lecture
|
Constraint Satisfaction B
|
Chapter 6.1-6.4, except 6.3.3
|
|
|
Wed 19 Oct
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 20 Oct
|
Quiz
#2
Lecture
|
Propositional Logic A |
Chapter 7.1-7.4 |
|
Fri 21 Oct
|
Discussion Section
|
Review, questions
|
|
|
Sun 23 Oct
|
First-Draft
AI deadine
|
First-Draft AI must run on
openlab.ics.uci.edu in the tournament shell and implement mini-max search
with depth cut-off and heuristic static evaluation function
|
|
6
|
Mon 24 Oct
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 25 Oct
|
Lecture
|
Propositional Logic B
|
Chapter 7.5 (optional: 7.6-7.8) |
|
|
Wed 26 Oct
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 27 Oct
|
Lecture
|
Mid-term
Exam Review
|
All
of above
|
|
Fri 28 Oct
|
Discussion Section
|
Review, questions
|
|
|
Sun 30 Oct
|
Alpha-beta
AI deadline
|
Alpha-beta AI must run on openlab.ics.uci.edu in the tournament shell and
extend First-Draft AI to include alpha-beta pruning
|
|
7
|
Mon 31 Oct
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
Happy Halloween! Wear a costume!
|
Tue 1 Nov
|
Mid-term
|
Mid-term
Exam
|
All
of above
|
|
|
Wed 3 Nov
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 3 Nov
|
Lecture
|
Predicate Logic A |
Chapter 8.1-8.5
|
|
Fri 4 Nov
|
Discussion Section
|
Review, questions
|
|
8
|
Mon 7 Nov
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 8 Nov
|
Lecture
|
Predicate Logic B |
Review Chapters 8.3-8.5, Read 9.1-9.2 (optional: 9.5)
|
|
|
Wed 9 Nov
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 10 Nov
|
Lecture
|
Probability, Uncertainty, Bayes Nets |
Chapters 13, 14.1-14.5
|
|
Fri 11 Nov
|
Discussion Section
|
Review, questions
|
|
|
Sun 13 Nov
|
IDS/Sorting
AI deadline
|
IDS/Sorting AI must run on openlab.ics.uci.edu
in the tournament shell and extend Alpha-beta AI to include IDS search up to
the time limit plus sort moves based on the last IDS iteration to put the
most favorable moves first for A/B pruning
|
|
9
|
Mon 14 Nov
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 15 Nov
|
Quiz
#3
Lecture
|
Machine Learning A |
Chapter 18.1-18.4 |
|
|
Wed 16 Nov
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 17 Nov
|
Lecture
|
Machine Learning B |
Chapters 18.5-12, 20.1-2
|
|
Fri 18Nov
|
Discussion Section
|
Review, questions
|
|
10
|
Mon 21 Nov
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 22 Nov
|
Lecture
|
Clustering, Regression
|
Chapter 18.6.1-2, 20.3.1
|
|
|
Wed 23 Nov
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 24 Nov
|
Holiday!
|
Happy Thanksgiving Holiday!
|
Rejoice, give thanks.
|
|
Fri 25 Nov
|
Holiday!
|
Happy Thanksgiving Holiday!
|
Rejoice, give thanks.
|
11
|
Mon 28 Nov
|
Project Clinic
|
Coding Project Clinic,
4-5pm, DBH-3013
|
|
Tue 29 Nov
|
Quiz
#4
Lecture
|
Special
Topics Lecture
(1) Special topics request from students;
(2) TA or Prof present their own research;
(3) Catch-up lecture if needed;
(4) Any other use desired.
|
TBA
|
|
|
Wed 30 Nov
|
Project Clinic
|
Coding Project Clinic,
5-6pm, DBH-3013
|
|
|
Thu 1 Dec
|
Lecture
|
Final
Exam Review
|
All of the above
|
|
Fri 2 Dec
|
Discussion Section
|
Review, questions
|
|
|
Sun 4 Dec
|
Final
AI deadline
|
Final AI must run on
openlab.ics.uci.edu in the tournament shell and extend IDS/Sorting AI to be
your best and final AI that will compete for you in the tournament.
Let
the Games begin!
|
|
12
|
Tue
6 Dec
|
Final
Exam
|
4:00
- 6:00 p.m.
|
All of the above
|
Thu., 22 Sep:
Lecture: Class setup,
Introduction, Agents.
Read
in advance: Textbook Chapters 1-2.
Lecture
slides: Introduction, Agents [PDF; PPT].
Fri., 23 Sep:
Discussion Section (required):
Review material for this week.
Week 1 Optional Mid-class Video
Break (show both for contrast):
IBM Watson: Final Jeopardy! and the Future of Watson
AI vs. AI.
Two chatbots talking to each other.
Week 1 Optional Cultural
Interest:
Alan Turing’s classic paper on AI (1950).
Alan Turing is the most famous computer scientist of all time.
The Turing Award is the highest honor in computer science.
The Turing Machine is still our fundamental theoretical model of computation.
Turing’s work on the
Enigma code in WWII led to programmable computers.
AAAI/AI
Topics: The Turing Test:
“Can Machines Think?”
Wikipedia
“Computing
Machinery and Intelligence”
John
McCarthy, “What
Is Artificial Intelligence?”
AAAI,
AI Overview.
Silicon Valley Kingpins Commit $1 Billion to Create Artificial Intelligence Without Profit Motive
Tue., 27 Sep:
Lecture: Intro to State
Space Search; Uninformed Search.
Read
in Advance: Textbook Chapter 3.1-3.4.
Lecture
slides (two parts):
(1)
Introduction to State Space Search [PDF; PPT]; and
(2)
Uninformed Search [PDF; PPT].
Thu., 29 Sep:
Lecture: Heuristic Search.
Read
in advance: Textbook Chapter
3.5-3.7.
Lecture
slides: Heuristic Search [PDF; PPT].
Fri., 30 Sep:
Discussion Section (required):
Review material for this week.
Week 2 Optional Ungraded
Homework:
Week 2 Optional Mid-class Video
Breaks:
Optional Mid-class Video Breaks for
Tue.
Interesting
search algorithm visualization web page (interactive demo).
Boston Dynamics Big Dog (new
video March 2008)
Optional Mid-class Video Breaks for
Thu.
Infinite Mario AI - Long
Level
An attempt at a Mario AI using the A* path-finding algorithm.
“You
can see the path it plans to go as a red line, which updates when it detects
new obstacles at the right screen border. It uses only information visible on
screen.”
See
also http://www.marioai.org/.
Week 2 Optional Cultural
Interest:
A*
Search in Interplanetary Trajectory Design, courtesy of Eric Trumbauer, former CS-271 student and Aero/Astro PhD
student.
Dr.
Trumbauer comments, “One thing to possibly
discuss with the last slide is that the itinerary it settles on does stay at a
higher energy for a little bit until it passes closest to Europa, maximizing
the velocity before the insertion sequence to the lower energy. This is indeed optimal behavior, as
opposed to immediately reducing its energy as a Greedy Best First algorithm using
this heuristic would want to do.”
A* Search in Protein
Structure Prediction, Lathrop and Smith, J. Mol. Biol
(JMB cover article) (read full paper).
Prof.
Lathrop comments, “The A* algorithm found and proved many global optimum
solutions for the difficult and important real-world problem of protein
structure prediction from sequence within two hours in search spaces
sizes as large as 10^20 to 10^30, which are search space sizes totally and
completely inaccessible to blind search methods.”
Tue., 4 Oct:
Lecture: Local Search.
Read in advance: Textbook Chapter 4.1-4.2.
Lecture
slides (two parts):
(1)
Local Search [PDF;
PPT];
and
(2)
Representation [PDF;
PPT].
Thu., 6 Oct:
Quiz #1 (answer key here).
Lecture: start Games/Adversarial Search.
Read
in advance: Textbook Chapter 5.1, 5.2, 5.4.
Lecture
slides: Games/Adversarial Search/MiniMax Search [PDF; PPT].
Fri., 7 Oct:
Discussion Section (required):
Review material for this week.
Heuristic Search and Local Search [PDF].
Sun., 9 Oct, 11:59pm: Project
“Minimal AI” due.
Tournament results are available here.
Week 3 Optional
Ungraded Homework:
Week 3 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“Boxcar 2D (show initially at the start of class, again at the
mid-class video break, and finally again at the end of class)”
The
program learns to build a car using a genetic algorithm. If you let this
program run for a long time (>> 30 generations), you will see that
eventually it produces cars well suited to the terrain.
This
outcome illustrates a general theme of genetic algorithms: very, very slow;
but, eventually, good performance. After all, it took ~3.6 billion years to
evolve humans from bacteria (http://en.wikipedia.org/wiki/Timeline_of_evolutionary_history_of_life).
Please
note that this eventual good performance of genetic algorithms is conditional
upon a representation that allows good solutions to sub-problems to be combined
simply, by cross-over, into a globally good solution; if the vector position of
the features is completely randomized within the chromosome, any such good
performance is lost.
Optional Mid-class
Non-video Break for Thu.
(Read the link aloud to the
class at the mid-class break.)
Arthur
C. Clarke “Quarantine.”
A science fiction short story, written by a classic master, in 188
words. He was challenged to write a science fiction short story that
would fit onto a postcard.
Week 3 Optional Cultural
Interest:
Newell & Simon’s “Symbols and Search” Turing
Award Lecture (1976).
Herbert Simon was awarded a Nobel Prize (in economics, 1978).
Minton,
et. al., 1990, AAAI "Classic
Paper" Award recipient in 2008.
How to solve the 1 Million Queens problem with local search.
Tue., 11 Oct.:
Lecture: finish
Games/Adversarial Search.
Read in advance: Textbook
Chapter 5.3. (Optional: Chapter 5.5 and beyond.)
Lecture
slides: Games/Adversarial Search/Alpha-Beta Pruning [PDF; PPT].
Thu., 13 Oct:
Lecture: start
Constraint Satisfaction.
Read in advance: Textbook
Chapter 6.1-6.4, except 6.3.3.
Lecture
slides: Constraint Satisfaction Problems [PDF;
PPT].
Fri., 14 Oct:
Discussion Section (required):
Review material for this week.
Week 4 Optional Ungraded
Homework:
Week 4 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
RoboCup
2012 Standard Platform: USA / Germany (Final).
Optional
Mid-class Video Break for Thu.
Week 4 Optional Cultural
Interest:
Campbell, et al., 2002, Artificial
Intelligence, “Deep Blue.” [PDF]
(URL http://www.sciencedirect.com/science/article/pii/S0004370201001291)
Details about the AI system that beat the human chess champion.
Chaslot, et al., “Monte-Carlo
Tree Search: A New Framework for Game AI”
in Proceedings of the Fourth Artificial Intelligence and
Interactive Digital Entertainment Conference, AAAI Press, Menlo Park, pp.
216-217, 2008.
An interesting combination of Local Search (Chapter 4) and Game
Search (Chapter 5).
Related URL: “Everything
Monte Carlo Tree Search” website.
Tue., 18 Oct.:
Lecture: finish Constraint
Satisfaction.
Read
in advance: Textbook Chapter 6.1-6.4, except 6.3.3.
Lecture
slides: Constraint Propagation [PDF;
PPT].
Thu., 20 Oct:
Quiz #2 (answer key here).
Lecture: start
Propositional Logic.
Read
in advance: Textbook Chapter 7.1-7.4.
Lecture slides: Propositional Logic A [PDF; PPT].
Fri., 21 Oct:
Discussion Section (required):
Review material for this week.
Sun., 23 Oct, 11:59pm: Project
“First-Draft AI” due.
Tournament results are available here.
Week 5 Optional Ungraded
Homework:
Week 5 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“Flexible Muscle Based Locomotion for Bipedal
Creatures” --- video
Optional Mid-class
Video Break for Thu.
Audi
Piloted Parking (Audi's self-parking car)
[DARPA] Alice's Crash
(spectator view)
Week 5 Optional Cultural
Interest:
“Flexible
Muscle-Based Locomotion for Bipedal Creatures” --- paper.
Autonomous car - Wikipedia,
the free encyclopedia
“Autonomous
Driving in Traffic: Boss and the Urban Challenge” (2009).
DARPA Urban Challenge
Highlights
[DARPA] Alice's Crash (road-finding
camera) [different view of Alice's Crash (spectator view); long]
[DARPA] Team Oshkosh attempts
forced Entry to Main Exchange
DARPA Urban Challenge: Ga
Tech hits curb
DARPA Urban Challenge - Sting
Racing crash
DARPA Urban Challenge Crash
Cornell MIT
DARPA Urban Challenge - robot
car wreck [different view of above]
View the
crashes above, then view these links with interest
tempered by great skepticism:
Tesla Model S P85D AWD and
auto-pilot demo
Google Car: It Drives Itself
- ABC News
[Part 1/3] The Evolution of Self-Driving
Vehicles
[Part 2/3] How Google's
Self-Driving Car Works
[Part 3/3] Google's
Self-Driving Golf Carts
Tue., 25 Oct.:
Lecture: finish
Propositional Logic.
Read
in advance: Textbook Chapter 7.5 (optional: 7.6-7.8).
Lecture slides: Propositional Logic B [PDF; PPT].
Thu., 27 Oct.:
Lecture: Review for Mid-term
Exam.
Read in advance: All of the above.
Lecture
slides: Review [PDF; PPT].
Fri., 28 Oct.:
Discussion Section (required):
Propositional Logic [PDF].
General Review and Questions for Mid-term Exam.
Sun., 30 Oct, 11:59pm: Project
“Alpha-beta AI” due.
Tournament results are available here.
Week 6 Optional Ungraded Homework:
Week 6 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“Janken (rock-paper-scissors) Robot with 100% winning
rate”
Optional Mid-class
Video Break for Thu.
“Asterisk - Omni-directional
Insect Robot Picks Up Prey #DigInfo”
“Freaky AI robot, taken from
Nova science now”
Hitting the road: Hitchbot begins cross-Canada journey
“Canada's
hitchBOT travels 4,000 miles to test human-robot
bonds --- LA Times.”
HitchBOT, the hitchhiking robot, gets beheaded in
Philadelphia
Tue., 1 Nov (No Project
Questions --- Full Time to Mid-term Exam):
Mid-term Exam (answer key here).
Read
in advance: All of the above.
Thu., 3 Nov:
Lecture: start
First Order Logic
Read in advance: Textbook Chapter 8.1-8.5.
Lecture
slides: First Order Logic Syntax [PDF; PPT].
Fri., 4 Nov:
Discussion Section (required):
Review material for this week.
Week 7 Optional Mid-class Video
Breaks:
No Mid-class Video Break for Tue. due to Mid-term Exam.
Optional Mid-class
Non-Video Break for Thu.
(Read the link aloud to the
class at the mid-class break.)
Ferrucci, et al., 2010, “Building
Watson: An Overview of the DeepQA Project”
Cyc is a large-scale knowledge-engineering project:
“CYC: A Large-Scale Investment in Knowledge Infrastructure,” Lenat, 1995
“Searching for Commonsense: Populating Cyc from the Web,” Matuszek et al, AAAI 2005
Cyc - Wikipedia, the free encyclopedia.
Tue., 8 Nov:
Lecture:
finish First Order Logic; Knowledge Representation.
Review Chapter 8.3-8.5
Read in advance: Textbook Chapter 9.1-9.2 (optional 9.5).
Lecture slides (two parts):
(1) First Order Logic Semantics [PDF; PPT]; and
(2)
First Order Logic Knowledge Representation [PDF;
PPT].
Thu., 10 Nov:
Lecture: Probability, Uncertainty, Bayesian Networks.
Read in advance: Textbook Chapters 13, 14.1-14.5.
Reasoning Under Uncertainty.
Bayesian Networks.
Fri., 11 Nov:
Discussion Section (required):
Review material for this week.
Sun., 13 Nov, 11:59pm: Project
“IDS/Sorting AI” due.
Tournament results are available here.
Week 8 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“Quadrocopter
Pole Acrobatics”
“Nano Quadcopter
Robots swarm video flying drones”
Optional Mid-class
Video Break for Thu.
The
Stanford Autonomous Helicopter performing an aerobatic airshow under computer
control:
“Stanford Autonomous
Helicopter - Airshow #1”
“Stanford Autonomous
Helicopter - Airshow #2 Redux”
Week 8 optional cultural
enrichment
Video of Judea Pearl’s 2011 Turing Award lecture.
The Mechanization of Causal Inference: A “mini” Turing Test and Beyond.
“Peter Norvig 12. Tools of AI: from logic to probability.”
Tue., 15 Nov:
Quiz #3 (answer key here).
Lecture: start Learning from
Examples.
Read in advance: Textbook Chapter 18.1-18.4.
Lecture
slides: Intro to Machine Learning [PDF; PPT].
Thu., 17 Nov:
Lecture: finish
Learning from Examples.
Read in advance: Textbook Chapter 18.5-18.12, 20.1-20.2.
Lecture slides:
Learning Classifiers [PDF; PPT].
Fri., 18 Nov:
Discussion Section (required):
Review material for this week.
Week 9 Optional Ungraded
Homework:
Week 9 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“A Swarm of One
Thousand Robots”
Optional Mid-class
Video Break for Thu.
Cheetah Robot runs 28.3 mph;
a bit faster than Usain Bolt
Week 9 optional cultural
enrichment
“Machine learning”
- Wikipedia, the free encyclopedia
“Data mining” -
Wikipedia, the free encyclopedia
Proof that Decision Tree information gain is always non-negative (problem 3, pp. 4-5).
Viola
& Jones, Learning, Boosting, Vision [PDF; PPT] (The
slide show describes a machine learning system that learns to recognize
scale-independent human faces in images at video streaming rates. For more information, read the two
papers immediately below)
Reading:
Viola & Jones, 2004, “Robust Real-Time
Face Detection”
Reading: Freund & Schapire, 1999, “A Short Introduction to Boosting”
Tue., 22 Nov:
Lecture: Clustering (unsupervised learning) and Regression (statistical numeric learning).
Read in advance: Textbook Chapters 18.6.1-2, 20.3.1.
Lecture
slides (two parts):
Clustering (Unsupervised Learning) [PDF; PPT].
Thu., 24 Nov:
Happy Thanksgiving Holiday!
Rejoice, give thanks.
Fri., 25 Nov:
Happy Thanksgiving Holiday!
Rejoice, give thanks.
Week 10 Optional Mid-class Video
Breaks:
Optional Mid-class
Video Break for Tue.
“Speech Recognition
Breakthrough for the Spoken, Translated Word”
No Mid-class Video Break for Thu., due to
Thanksgiving Holiday.
Week 10 Optional Cultural
Enrichment:
As
always, view self-promotional materials with a great deal of
skepticism. It is easy to
make a computer that can program itself (for better or worse --- often
worse). It is hard to make a
computer that can program itself “for better, correctly and
intelligently.” You be the
judge.
“Google
reveals it is developing a computer so smart it can program ITSELF.”
As
always, view self-promotional materials with a great deal of skepticism. Consider the remarks directly above as
you view the links below. You be
the judge.
“IBM
simulates 530 billon neurons, 100 trillion synapses on supercomputer”
Tue., 29 Nov:
Quiz #4 (answer key here).
Lecture:
Special Topics Lecture
(1) Special topics request from students;
(2)
TA or Prof present their own research;
(3)
Catch-up lecture if needed;
(4)
Any other use desired.
Thu., 1 Dec:
Lecture: Review for Final Exam.
Read in advance: All of the above.
Lecture
slides: Review [PDF; PPT].
Fri., 2 Dec:
Discussion Section (required):
Review for Final Exam.
Sun., 4 Dec: Project
“Final AI” due. Tournament results are available here.
Week 11 No Optional Mid-class Video
Breaks Due to End of Quarter
Week 11 No Optional Cultural Interest Due to End of Quarter
Tue., 6 Dec., 4:00 - 6:00 p.m.
(answer key here).
Your project is to code
a “Connect-K” agent.
Project Coding Shells:
Student resources are
available here,
including:
v General documentation and background
info.
v A C++ shell.
v A Java shell.
v A Python shell.
v A tournament shell.
We will fix any further
problems and issue new shells as necessary. Please watch for and download any
new shells, then discard your old shells. You can keep any “smart”
code you have written, just put it into the new shells.
“Dumb”
coding shells are available in C++, Java, and Python. You must write the “smarts.”
To help you get started, we also have released the source code to “RandomAI,” and the executables to RandomAI,
PoorAI, AverageAI, and GoodAI (they go by different names in different shells). Your
final AI will compete in a tournament against all your classmates for extra
credit bonus points (the top 10% will get 10 Bonus points, the second 10% will
get 9, the third 10% will get 8, and so on). This is a solo or pair project
and you must do all of it all by yourself or with one partner.
As
noted in lecture, all of my CS-171 project shells were written by former CS-171
students (grade of A- or better required) who wanted to go further and do
something creative and interesting. The original Java shell was written by XXXX. The Python shell was
written by XXXX. The C++ shell was
written by XXXX, then revised by XXXX. The tournament
shell was written by XXXX.
Project Deadlines and Regulations:
·
Project
deadlines are given above in the “Syllabus
Overview and Important Dates” section.
·
Your EEE DropBox submission must be a single “zipped”
file named “yourLastName_yourUCINumericID_yourTeamName.” NO SPACES OR ANY OTHER SPECIAL UNIX
CHARACTER in yourTeamName. Please restrict your TeamName to characters, digits, hyphen, and underscore, or
else you may lose points.
·
It should have three
subdirectories: src, bin, & doc; for source,
executable, and documents (‘doc’
must contain your Project Report).
·
Your main AI file must
contain the string “AI” and no other file may contain the string
“AI” (case is ignored, i.e., “ai”
== “AI”).
You will lose 10% of
your project score for each day (or part thereof) that your project is late for
any deadline. Please submit your project early, well ahead of the deadline, and
avoid the last-minute rush. If system problems, web congestion, or other
unavoidable Internet delays make your project late, it is still late and will
be penalized.
Previous
CS-171 Quizzes, Mid-term exams, and Final exams are available here as study
guides.
As an
incentive to study this material, at least one question from a previous Quiz or
Exam will appear on every new Quiz or Exam. In particular, questions that many
students missed are likely to appear again. If you missed a question, please
study it carefully and learn from your mistake --- so that if it appears again,
you will understand it perfectly.
Please note
that some of the very old tests below reflect different textbooks that may
define some things differently than does your current textbook. In case of
conflict, your current textbook is deemed correct and will prevail. Some of
your visualization systems may not display the red PDF overlays used to correct
errors in very old tests. For example, in problems #2a, #2c, #3a, and #3b on
Quiz #2 from SQ’2004, the PDF overlay is invisible on a Mac (iPad), and
possibly on some other systems or printers. The PDF overlays just do not seem to
work as advertised (sorry!!), but this problem seems only to afflict very old
tests (i.e., from over a decade ago). If you are confused by any of the answers
below, please bring your questions to the TA in Discussion Section
(required). If you find a genuine
error anywhere, please send me email and you will receive a Bonus Point if
correct.
Also, a
student has recommended ‘quizlet.com’ as a good online study
resource. While I cannot vouch for it, apparently it contains several good
study aids for your textbook.
Summer Session I 2016:
Mid-term Exam and key.
Final Exam and key.
Winter Quarter 2016:
Mid-term Exam and key.
Final Exam and key.
Fall Quarter 2015:
Mid-term Exam and key.
Final Exam and key.
Winter Quarter 2015:
Mid-term Exam and key.
Final Exam and key.
Fall Quarter 2014:
Mid-term Exam and key.
Final Exam and key.
Winter Quarter 2014:
Mid-term
Exam and key
Final
Exam and key
Fall Quarter 2013:
Mid-term
Exam and key
Final Exam and key
Fall Quarter 2012:
Mid-term Exam and key
Final
Exam and key
Winter Quarter 2012:
Mid-term Exam and key
Final Exam and key
Spring Quarter 2011:
Mid-term Exam and key
Final
Exam and key
Spring Quarter 2004:
The correct
answer to Quiz #2 (2a) is A B D E C G.
The correct
answer to Quiz #2 (2c) is A; A B C G.
The correct
answer to Quiz #2 (3a) is N.
The correct
answer to Quiz #2 (3b) is N.
These emendations to Quiz #2 have been corrected by overlays to the old PDF files, but apparently those corrections may not be not visible on some systems (MAC/iPAD?) or when printed on some printers (?). Please be warned.
Spring Quarter 2000:
Additional Online Resources may be posted as the class progresses.
Textbook website for Artificial Intelligence: A Modern Approach (AIMA).
AAAI
Digital Library of more
than 10,000 AI technical papers.
AAAI AI Magazine.
AAAI Author Kit.