Professor:Eric
Eaton Office: I will be borrowing Lisa Meeden's office in the
evenings, Science Center 243 Office Hours: Tuesdays and Thursdays 6:00pm-6:50pm, and
by appointment. E-mail:
(Please put "CS63" at the start of the subject line)
E-mail is the best way to reach me, and I make a concerted
effort to respond to all e-mails within 24 hours (often, much
less!). Primarily, I will be on-campus and available in the
evenings, although we can make other special arrangements as
needed. During the day, I work as a research scientist at a
local AI research laboratory. Often, it may not be possible
for me to respond to e-mails weekdays between 8am - 5pm, so
most replies will come in the evenings.
Course Description
Swarthmore catalog description: Artificial
intelligence (AI) can be defined as the branch of computer
science that is concerned with the automation of intelligent
behavior. Intelligent behavior encompasses a wide range of
abilities; as a result, AI has become a very broad field that
includes game playing, automated reasoning, expert systems,
natural language processing, modeling human performance (cognitive
science), planning, and robotics. This course will focus on
a subset of these topics and specifically on machine learning,
which is concerned with the problem of how to create programs
that automatically improve with experience. Machine learning
approaches studied will include neural networks, decision trees,
genetic algorithms, and reinforcement techniques.
Artificial Intelligence
is, in my opinion, the coolest and most exciting subfield of
computer science. In this course,
we will explore several major areas of AI, including search,
game playing, knowledge representation and reasoning, planning,
and machine learning. We will also relate
these topics to their applications in robotics, computer gaming,
medical diagnosis, computer vision, natural language understanding,
and many other areas. Google, NSA, and NASA all use AI technology.
AI's successes, such as the IBM
Deep Blue chess program beating Kasparov (1996),
the DARPA Urban Challenge
(2007) and Grand Challenge (2005, 2004) autonomous vehicle
competitions,
and
solving
checkers (2007) are
well-publicized and very popular.
Paul Graham, 1995. ANSI Common Lisp,
Prentice Hall. ISBN: 0-13-370875-6.
This is an excellent book for learning lisp, and is available
only in a print version. I'm not requiring it for this
course, since Practical Common Lisp is available online.
This is the reference manual for Common Lisp.
It isn't required for the course, since most of you will
find the online version sufficient as a resource, but
there is a print version if you like real books.
A background in probability, statistics, and linear algebra would be helpful,
but it isn't required. Those of you without this background might have to work
a bit harder when we get to those sections of the course.
Course Outline
The course will be broken up into the following rough sections:
Search, heuristics, game playing (4 weeks)
Knowledge representation and reasoning, theorem proving,
planning (3 weeks)
A course mailing list (cs63@cs.swarthmore.edu) has
been established for distributing news and discussing course-related
topics. Please post general
problems, news articles, questions, and answers to the list
for the benefit of the entire class. At no time
should students post homework solutions
or solutions to exam questions to the course mailing list;
posting such solutions will, of course, be
interpreted as academic dishonesty.
Posting such solutions will be the sole responsibility of the
course staff.
Please e-mail individual concerns directly to me.
I have already subscribed everyone who was registered for
the course as of August 30th; if you joined us afterward or
would prefer to register another e-mail address, please let
me know.
Communication
Attendance and active participation are expected in every
class. Participation includes asking questions,
contributing answers, proposing ideas,
and
providing
constructive
comments.
As you will discover, I am a proponent of two-way
communication and I welcome feedback during the semester
about the course. I am available to answer student
questions, listen to concerns, and talk about any course-related
topic (or otherwise!). Come
to office hours! This
helps me get to know you. You are welcome to stop by
and chat. There are many more exciting topics to talk about
that we won't have
time to
cover in-class.
Whenever you e-mail me, please use a meaningful subject line
and include the phrase "CS63" at the beginning of
that line. Your e-mail will catch my attention and I will respond quicker if
you do this. I make an effort to respond to e-mails within
24 hours. Since I work at a research lab during the day, most
of my replies will come in the evening.
Although computer science work can be intense and solitary,
please stay in touch with me, particularly if you feel stuck
on a
topic
or
project
and
can't
figure out
how
to
proceed.
Often a quick e-mail, phone call or face-to-face conference
can reveal solutions to problems and generate renewed creative
and scholarly energy. I strongly recommend
beginning homeworks and projects early, since we will be
covering a variety of challenging topics in this course.
Incomplete grades will be given only for verifiable medical
illness or other such dire circumstances.
Homework Assignments
There will be six (6) homeworks assigned over the course of the
semester. Each homework will be assigned at least one week in advance
of its due date. The homework assignments will be a mix of written, programming,
and analytical components.
Homework assignment solutions must be turned in at the start
of class in typeset hardcopy on the designated due
date. Code will be submitted using the handin63 program.
Homework assignments can be submitted up to 24 hours late for
a 25% penalty,
and 48
hours late for
a 50% penalty. No submissions later than 48 hours will be
accepted. Extensions will be given only in the
case of verifiable medical excuses or other such dire
circumstances, if requested in advance.
0-24 hours late: 25% penalty
24-48 hours late: 50% penalty
more than 48 hours late: no credit
Penalties are applied by taking off that percentage of the points you would have earned: your_score_without_penalty * (1 - penalty) = your_score_with_penalty.
For example, if you would have earned a 90% on the assignment, but you turned it in 5 hours late, your score would be 90% * (1 - 0.25) = 67.5%.
All homework solutions must be typeset. Any solutions requiring math or proofs must use proper
mathematical notation. Similarly, graphs should be well-constructed with all axes properly labeled.
I highly recommend the use of the LaTeX text formatting system, but you can use any program capable
of producing proper mathematical notation. The main course page contains links to good LaTeX
websites and links to example files.
All solutions are required to be your own, individual work.
I encourage you to discuss methods, concepts, and
assignments with anyone; however, the solutions turned in must
be your own
work.
A good rule of thumb is to be alone when you sit down to actually
generate solutions to the assigned problems, and to not show
your solutions
to anyone else.
At the top of your submission, you must include a clear statement specifying
the source of any assistance you received on this assignment. This includes any
websites you consulted, other students with whom you discussed any of the
problems, etc. If you did not receive any assistance, you must say so.
Submissions without this statement will be penalized
Exams
There will be one midterm and a final exam. The exams will
be closed-book and closed-notes. In the case of verifiable
medical excuses or other such dire circumstances, arrangements
must be made with the instructor for a makeup exam before the
test date.
Exams will cover material from lectures, homeworks, and assigned readings (including topics
not discussed in-class). So, keep up with those readings!
Academic Honesty and Legitimate Collaborations
Swarthmore CS Department's Academic Integrity Policy: Under
no circumstances may you hand in work done with (or by) someone
else under your own name. Your code should never
be shared with anyone; you may not examine or use code belonging
to someone else, nor may you let anyone else look at or make
a copy of your code. This includes sharing solutions after
the due date of the assignment. Failure to abide by these
rules constitutes academic dishonesty and will lead to a
hearing of the College Judiciary Committee. According to
the Faculty Handbook: "Because plagiarism is considered
to be so serious a transgression, it is the opinion of the
faculty that for the first offense, failure in the course
and, as appropriate, suspension for a semester or deprivation
of the degree in that year is suitable; for a second offense,
the penalty should normally be expulsion."
All this being said about academic honesty, I do want to encourage
you to discuss the material and work together to understand
it.
Here
are my
thoughts
on
collaborating with other students:
The readings and lecture topics are group work. Please discuss
the readings and associated topics with each other. Work together
to understand the material. I highly recommend forming a reading
group of 3-5 people -- we will explore many challenging
ideas in AI and it helps to have multiple people working together
to understand them.
It is fine to discuss the topics covered in the homeworks,
to discuss approaches to problems, and to sketch out general solutions.
However, you MUST write up the homework answers, solutions,
and programs individually. You are not permitted to share specific
solutions, mathematical results, program code,
knowledge representations, experimental results, etc. If you
made any notes or worked out something on a white board with
another person while you were discussing the homework, you
shouldn't use those notes while writing up your answer, however
tempted you may be to do so.
You are fully permitted to (and should!) discuss the project with members of your team. I also encourage you to work outside of your team to
understand the other topics in the course. However, remember that there will be a competition, so you don't want to give other teams any of your good ideas!
Exams, of course, must be your own individual work.
If you have any questions as to what types of collaborations are allowed and which are dishonest, please ask me before you make a mistake.
Acknowledgements
Thanks to Marie desJardins, Tim Finin, and Terran Lane for making their course materials available. Many of the course materials
for this class have been adapted from those sources.
