Recent Changes - Search:
ECG Home

GitHub

People

Publications

Calendar

Projects

Fall 2017

Older Courses

Spring 2017

Fall 2016

Spring 2016

Fall 2015

Spring 2015

Fall 2014

Spring 2014

Fall 2013

Spring 2013

Fall 2012

Spring 2012

Fall 2011

Spring 2011

Fall 2010

Spring 2010

Fall 2009

Spring 2009

Fall 2008

Spring 2008

Fall 2007

HOWTOs

edit SideBar

AIfall12

AIfall12.AIfall12 History

Hide minor edits - Show changes to output

Changed line 5 from:
TA''tba'' \\
to:
GraderSimone Hill \\
Changed lines 37-39 from:
The authors have recently published the third edition of ''AIMA''. I do recommend this new edition. New and used copies are available at the UML bookstore, or online (3rd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn= 0136042597]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-3rd/dp/0136042597/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn= 0136042597&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'')

It
would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (2nd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
to:
The authors have recently published the third edition of ''AIMA''. I do recommend this new edition. New and used copies are available at the UML bookstore, or online (3rd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn= 0136042597]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-3rd/dp/0136042597/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn= 0136042597&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').

It
would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (2nd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').

Please do not use the first edition.
Changed lines 37-38 from:
The authors have recently published the third edition of ''AIMA''. I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
to:
The authors have recently published the third edition of ''AIMA''. I do recommend this new edition. New and used copies are available at the UML bookstore, or online (3rd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn= 0136042597]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-3rd/dp/0136042597/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn= 0136042597&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'')

It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping
(2nd edition: ''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
Changed line 123 from:
The group address is mailto:uml-ai-fall12@googlegroups.com.  You have to be a member to send to the list.
to:
The group address is mailto:uml-ai-fall12@googlegroups.com.  You have to be a member to send to the list.
Added lines 70-83:
!!Undergraduate Project Sequence

For undergraduates, 91.420 Artificial Intelligence can be grouped with 91.421 Machine Learning ''or'' 91.450 Robotics I to form a course pair.

!!Graduate Group

For graduate students, 91.543 is in Group IV, “Information Management and Analysis.”

!!Collaboration and Academic Integrity Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.

Please be familiar with the university's academic integrity policy [[for undergraduates->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]] or [[for graduate students->http://www.uml.edu/catalog/graduate/policies/academic_dishonesty.htm]].

Deleted lines 121-134:

!!Undergraduate Project Sequence

For undergraduates, 91.420 Artificial Intelligence can be grouped with 91.421 Machine Learning ''or'' 91.450 Robotics I to form a course pair.

!!Graduate Group

For graduate students, 91.543 is in Group IV, “Information Management and Analysis.”

!!Collaboration and Academic Integrity Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.

Please be familiar with the university's academic integrity policy [[for undergraduates->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]] or [[for graduate students->http://www.uml.edu/catalog/graduate/policies/academic_dishonesty.htm]].
Changed lines 72-76 from:
We will use Google Groups for class conversation and announcements.  Please join this group.  ''I'd advise setting your preferences to immediate, individual delivery of messages—click the “Edit my membership” tab to do this.''
to:
We will use Google Groups for announcements and discussion of material outside of class.

Please join the group by entering
your email address in the box below, and following the subsequent confirmation instructions. 

''I strongly advise that you set your email delivery
preferences to immediate, individual delivery of messages—click the “Edit my membership” tab to do this.''
Changed line 72 from:
We will use Google Groups for class conversation and announcements.  Please join this group.  '''I'd advise setting your preferences to immediate, individual delivery of messages—click the “Edit my membership” tab to do this.'''
to:
We will use Google Groups for class conversation and announcements.  Please join this group.  ''I'd advise setting your preferences to immediate, individual delivery of messages—click the “Edit my membership” tab to do this.''
Changed lines 43-44 from:
There are three major categories of work that will be assessed.  These are:
to:
There are five categories of work that will be assessed.  These are:
Changed lines 47-48 from:
* '''Literature review assignment, 10%.'''  You will read three papers related to an area of AI in which you are interested, and prepare conference-style reviews of the papers.  (One of the papers will be selected from a set that I specify, and you will select two other papers.)  This work be practice for literature searches for your final project, and help you think about how to build on and cite previous work.
to:
* '''Literature review assignments, 10%.'''  You will read three papers related to an area of AI in which you are interested, and prepare conference-style reviews of the papers.  (One of the papers will be selected from a set that I specify, and you will select two other papers.)  Also, you will review each others' project proposal documents. This work be practice for literature searches for your final project, and help you think about how to build on and cite previous work.
Changed line 62 from:
10% Literature review assignment \\
to:
10% Literature review assignments \\
Changed lines 72-73 from:
We will use Google Groups for class conversation and announcements.  Please join this group.  I'd advise setting your preferences to immediate, individual delivery of messages—click the “Edit my membership” tab.
to:
We will use Google Groups for class conversation and announcements.  Please join this group.  '''I'd advise setting your preferences to immediate, individual delivery of messages—click the “Edit my membership” tab to do this.'''
Changed lines 113-115 from:
!!Collaboration Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other
side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.  Please be familiar with the university's academic integrity policy [[for undergraduates->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]] or [[for graduate students->http://www.uml.edu/catalog/graduate/policies/academic_dishonesty.htm]].
to:
!!Collaboration and Academic Integrity Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other
side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.

Please be familiar with the university's academic integrity policy [[for undergraduates->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]] or [[for graduate students->http://www.uml.edu/catalog/graduate/policies/academic_dishonesty.htm]].
Added line 22:
* probabilistic reasoning, including Markov Decision Processes (MDPs) and Hidden Markov Models (HMMs)
Changed lines 24-25 from:
* probabilistic reasoning, including hidden Markov models
to:
Changed lines 31-32 from:
A big part of AI is not just knowing a collection of approaches, but understanding which approach is right for which problem. There will be a significant semester project where you will apply ideas from the course to a problem of your own choosing.
to:
A big part of AI is not just knowing a collection of approaches, but understanding which approach is right for which problem. To encourage the development of these skills, there will be a significant semester project where you will apply ideas from the course to a problem of your own choosing.
Changed lines 37-38 from:
The authors have recently published the third edition of “AIMA.” I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
to:
The authors have recently published the third edition of ''AIMA''. I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
Changed lines 45-52 from:
* '''Weekly (or semi-weekly) assignments, 25%.'''  It is my opinion that the primary way to really learn new material is by working through assignments.  Assignments will be accepted up to one week late with a 25% reduction in that assignment's value.  ''If you fall behind on your homework, it is much better to cut your losses and work on the current assignment, instead of running behind trying to catch up.''

* '''Daily reading reports and brief presentations, 10%.''' We will be reading the Minsky book at the rate of approx. 7 sections chapters per class meeting.  (Each section is exactly one page in length.)  Each of you will prepare 140-character synopses of each section, assigned at each class and due on the next one.  Each day, I will randomly call on a person to lead a short discussion the assigned material.  Please have your synopses at hand for each class meeting; you may start the discussion by reading them.  You can expect to lead about twice over the course of the semester.  Please be prepared.

* '''Quizzes and a final exam, 30%.''' There will be two in-class quizzes during the semester. There will be a cumulative final, worth 20% of your overall grade.

* '''Term project, 30%.'''
A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.
to:
* '''Programming assignments, 25%.'''  It is my opinion that the primary way to really learn new material is by working through assignments.  Assignments will be accepted up to one week late with a 25% reduction in that assignment's value.  ''If you fall behind on your homework, it is much better to cut your losses and work on the current assignment, instead of running behind trying to catch up.''

* '''Literature review assignment, 10%.'''  You will read three papers related to an area of AI in which you are interested, and prepare conference-style reviews of the papers.  (One of the papers will be selected from a set that I specify, and you will select two other papers.)  This work be practice for literature searches for your final project, and help you think about how to build on and cite previous work.

* '''Daily reading reports and brief presentations, 10%.''' We will be reading
the Minsky book at the rate of approx. 10 sections/chapters per class meeting.  (Each section is exactly one page in length.)  Each of you will prepare 140-character synopses of each section, assigned at each class and due on the next one.  Each day, I will randomly call on one or more persons to lead a short discussion the assigned material.  Please have your synopses at hand for each class meeting; you may start the discussion by reading them.  You can expect to lead three or four times over the course of the semester.  Please be prepared.

* '''Midterm and final exam, 25%.''' There will a midterm and final, together worth 25% of your overall grade.

* '''Term project, 25
%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.
Changed lines 61-62 from:
25% Weekly homeworks \\
to:
25% Programming assignments \\
10% Literature review assignment
\\
Changed lines 64-66 from:
10% Two quizzes \\
20% Final \\
30
% Project \\
to:
25% Midterm and final \\
25% Project \\
Changed lines 67-69 from:
to:
----- \\
100% Total

Deleted line 115:
Changed line 5 from:
TA:  '''tba''' \\
to:
TA:  ''tba'' \\
Changed lines 25-28 from:
Ideas will be developed theoretically and with practical programming challenges using the U.C. Berkeley ’Pac-Man projects,“ in which you program a progressive series of challenges inspired by the original Pac-Man arcade game.

These problem sets ’teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underlie real-world application areas such as natural language processing, computer vision, and robotics“ (see http://www-inst.eecs.berkeley.edu/~cs188/pacman/pacman.html).
to:
Ideas will be developed theoretically and with practical programming challenges using the U.C. Berkeley “Pac-Man projects,” in which you program a progressive series of challenges inspired by the original Pac-Man arcade game.

These problem sets “teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underlie real-world application areas such as natural language processing, computer vision, and robotics” (see http://www-inst.eecs.berkeley.edu/~cs188/pacman/pacman.html).
Added lines 33-34:
!!Texts
Deleted lines 40-46:
The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include:

* search
* game-playing, including adversarial and stochastic search
* reinforcement learning, including value iteration and q-learning
* probabilistic reasoning, including hidden Markov models

Added line 112:
Changed lines 5-7 from:
TA:  '''tba'''
Tue/ThuMon/Wed/Fri, 12:30p–1:45p, OS403
to:
TA:  '''tba''' \\
Tue/Thu, 12:30p–1:45p, OS403
Changed lines 18-27 from:
In this class, we will focus on the practical.  The goal will be to illustrate all ideas with code that runs.  Examples in class will be worked out in Python and Lisp (probably leaning more towards the Python).  Sample code for many of the algorithms discussed in the text is provided in a variety of languages (Python and Lisp, plus Java, C++, and C#).  You will be allowed to complete assignments using the language of your choice, and you will be welcome to use the reference code as a basis for your own experiments and extensions,

The textbook, as noted above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of “AIMA.”  I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the “father of AI,” and this work lays the foundation for “strong AI”—the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky’s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).''

The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include
:
to:
One organizing principle across the field is the formalization of real-world problems based on utility functions, and then the use of various techniques to maximize expected utility. Based on this unifying theme, we will study:
Added lines 25-45:
Ideas will be developed theoretically and with practical programming challenges using the U.C. Berkeley ’Pac-Man projects,“ in which you program a progressive series of challenges inspired by the original Pac-Man arcade game.

These problem sets ’teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underlie real-world application areas such as natural language processing, computer vision, and robotics“ (see http://www-inst.eecs.berkeley.edu/~cs188/pacman/pacman.html).

Coding will be done in Python (which you can learn during the class if you don't know it yet).

A big part of AI is not just knowing a collection of approaches, but understanding which approach is right for which problem. There will be a significant semester project where you will apply ideas from the course to a problem of your own choosing.

The textbook, as shown above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig. The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter. It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of “AIMA.”  I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the “father of AI,” and this work lays the foundation for “strong AI”—the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky’s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).''

The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include:

* search
* game-playing, including adversarial and stochastic search
* reinforcement learning, including value iteration and q-learning
* probabilistic reasoning, including hidden Markov models

Deleted line 116:
Deleted lines 0-111:
[[AIfall12|Home]] [[Assignments]] [[Lecture Blog]] [[Resources]] [[Project]] [[http://groups.google.com/group/uml-ai-fall12 | Discussion Group]]

91.420/91.543 Artificial Intelligence, Fall 2012 \\
'''Prof. Fred Martin''', (:html:)<a href="http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=" onclick="window.open('http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=', '', 'toolbar=0,scrollbars=0,location=0,statusbar=0, menubar=0,resizable=0,width=500,height=300'); return false;" title="Reveal this e-mail address">click for fred's email</a>(:htmlend:) \\
TA:  ''tba'' \\
Tue/ThuMon/Wed/Fri, 12:30p&#150;1:45p, OS403

We will be using the following books:

|| border=0 width=100% cellpadding=10
|| '''Artificial Intelligence: A Modern Approach''' (3rd edition &#150; 2009) [[<<]] Stuart Russell and Peter Norvig  [[<<]] %height=150px% [[http://aima.cs.berkeley.edu/ | Attach:aima-cover.jpg]] || '''The Society of Mind''' (1987) [[<<]] Marvin Minsky [[<<]] %height=150px% [[http://web.media.mit.edu/~minsky/ | Attach:som-minsky.jpg]]
|| By far the best AI text. || &#147;The mind is what the brain does.&#148;&#151;Steven Pinker

!!What is AI?

There are few areas in computer science as broad as artificial intelligence.  AI encompasses algorithm design, agents and robots, natural language understanding, expert systems, music and sound, as well as philosophical questions about the nature of consciousness!

One organizing principle across the field is the formalization of real-world problems based on utility functions, and then the use of various techniques to maximize expected utility.  Based on this unifying theme, we will study:

* search
* game-playing, including adversarial and stochastic search
* reinforcement learning, including value iteration and q-learning
* probabilistic reasoning, including hidden Markov models

Ideas will be developed theoretically and with practical programming challenges using the U.C. Berkeley &#146;Pac-Man projects,&#147; in which you program a progressive series of challenges inspired by the original Pac-Man arcade game.

These problem sets &#146;teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underlie real-world application areas such as natural language processing, computer vision, and robotics&#147; (see http://www-inst.eecs.berkeley.edu/~cs188/pacman/pacman.html).

Coding will be done in Python (which you can learn during the class if you don't know it yet).

A big part of AI is not just knowing a collection of approaches, but understanding which approach is right for which problem. There will be a significant semester project where you will apply ideas from the course to a problem of your own choosing.

The textbook, as shown above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. ''New and used copies are available at the UML bookstore.''  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).


!!Grading

There are three major categories of work that will be assessed.  These are:

* '''Weekly (or semi-weekly) assignments, 25%.'''  It is my opinion that the primary way to really learn new material is by working through assignments.  Assignments will be accepted up to one week late with a 25% reduction in that assignment's value.  ''If you fall behind on your homework, it is much better to cut your losses and work on the current assignment, instead of running behind trying to catch up.''

* '''Daily reading reports and brief presentations, 10%.''' We will be reading the Minsky book at the rate of approx. 7 sections chapters per class meeting.  (Each section is exactly one page in length.)  Each of you will prepare 140-character synopses of each section, assigned at each class and due on the next one.  Each day, I will randomly call on a person to lead a short discussion the assigned material.  Please have your synopses at hand for each class meeting; you may start the discussion by reading them.  You can expect to lead about twice over the course of the semester.  Please be prepared.

* '''Quizzes and a final exam, 30%.''' There will be two in-class quizzes during the semester. There will be a cumulative final, worth 20% of your overall grade.

<* '''Term project, 30%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.

->In the final project, you will apply the ideas developed in the class in an original software implementation. You may thus connect the ideas of the class with your own interests&#151;music, robotics, art, databases, the web, networking, gaming, etc. The learning goal of the project is to have you find some real-world relevance of the ideas in the class.

Classroom participation is worth 5% of your overall grade.  In practice, if your other grades put you on a marking boundary, this will push it one way or the other.

To summarize:

25% Weekly homeworks \\
10% Minsky reports \\
10% Two quizzes \\
20% Final \\
30% Project \\
5% Classroom participation \\

!!Discussion Group / E-Mail List

We will use Google Groups for class conversation and announcements.  Please join this group.  I'd advise setting your preferences to immediate, individual delivery of messages&#151;click the &#147;Edit my membership&#148; tab.

(:html:)
<table style="border:1px solid #aa0033; font-size:small" align=center>
  <tr>
    <td rowspan=3>
    <img src="http://groups.google.com/groups/img/groups_medium.gif" height=58 width=150 alt="Google Groups">
    </td>
    <td colspan=2 align=center><b>Subscribe to uml-ai-fall12</b></td>
  </tr>
  <form action="http://groups.google.com/group/uml-ai-fall12/boxsubscribe">
  <tr>
    <td>Email: <input type=text name=email></td>
    <td>
      <table
      style="background-color:#ffcc33;padding:2px;border:2px outset #ffcc33;">
      <tr>
        <td>
        <input type=submit name="sub" value="Request">
        </td>
      </tr>
      </table>
    </td>
  </tr>
  </form>
  <tr><td colspan=2 align=center>
  <a href="http://groups.google.com/group/uml-ai-fall12" target="new">Browse Archives</a>
  </td></tr>
</table>
(:htmlend:)

The group address is mailto:uml-ai-fall12@googlegroups.com.  You have to be a member to send to the list.

!!Project Sequence

For undergraduates, 91.420 Artificial Intelligence can be grouped with 91.450 Robotics I to form a course pair.


!!Collaboration Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.  Please be familiar with the university's [[academic integrity policy->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]].

!!Graduate Section

The graduate section is 91.543.201.  In addition to being treated as honors students, students who are registered in the graduate section will locate, read, and report on current and/or historical research papers associated with each of the topics in the class.  Also, you will prepare a paper of your own, based on your implementation project.

Changed lines 18-27 from:
In this class, we will focus on the practical.  The goal will be to illustrate all ideas with code that runs.  Examples in class will be worked out in Python and Lisp (probably leaning more towards the Python).  Sample code for many of the algorithms discussed in the text is provided in a variety of languages (Python and Lisp, plus Java, C++, and C#).  You will be allowed to complete assignments using the language of your choice, and you will be welcome to use the reference code as a basis for your own experiments and extensions,

The textbook, as noted above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. ''New and used copies are available at the UML bookstore.''  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).

The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include
:
to:
One organizing principle across the field is the formalization of real-world problems based on utility functions, and then the use of various techniques to maximize expected utility.  Based on this unifying theme, we will study:
Added lines 25-39:
Ideas will be developed theoretically and with practical programming challenges using the U.C. Berkeley &#146;Pac-Man projects,&#147; in which you program a progressive series of challenges inspired by the original Pac-Man arcade game.

These problem sets &#146;teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underlie real-world application areas such as natural language processing, computer vision, and robotics&#147; (see http://www-inst.eecs.berkeley.edu/~cs188/pacman/pacman.html).

Coding will be done in Python (which you can learn during the class if you don't know it yet).

A big part of AI is not just knowing a collection of approaches, but understanding which approach is right for which problem. There will be a significant semester project where you will apply ideas from the course to a problem of your own choosing.

The textbook, as shown above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. ''New and used copies are available at the UML bookstore.''  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).

Changed lines 50-51 from:
* '''Term project, 30%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.
to:
<* '''Term project, 30%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.
Added lines 112-215:

[[AIfall12|Home]] [[Assignments]] [[Lecture Blog]] [[Resources]] [[Project]] [[http://groups.google.com/group/uml-ai-fall12 | Discussion Group]]

91.420/91.543 Artificial Intelligence, Fall 2012 \\
'''Prof. Fred Martin''', (:html:)<a href="http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=" onclick="window.open('http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=', '', 'toolbar=0,scrollbars=0,location=0,statusbar=0, menubar=0,resizable=0,width=500,height=300'); return false;" title="Reveal this e-mail address">click for fred's email</a>(:htmlend:) \\
TA:  '''tba'''
Tue/ThuMon/Wed/Fri, 12:30p&#150;1:45p, OS403

We will be using the following books:

|| border=0 width=100% cellpadding=10
|| '''Artificial Intelligence: A Modern Approach''' (3rd edition &#150; 2009) [[<<]] Stuart Russell and Peter Norvig  [[<<]] %height=150px% [[http://aima.cs.berkeley.edu/ | Attach:aima-cover.jpg]] || '''The Society of Mind''' (1987) [[<<]] Marvin Minsky [[<<]] %height=150px% [[http://web.media.mit.edu/~minsky/ | Attach:som-minsky.jpg]]
|| By far the best AI text. || &#147;The mind is what the brain does.&#148;&#151;Steven Pinker

!!What is AI?

There are few areas in computer science as broad as artificial intelligence.  AI encompasses algorithm design, agents and robots, natural language understanding, expert systems, music and sound, as well as philosophical questions about the nature of consciousness!

In this class, we will focus on the practical.  The goal will be to illustrate all ideas with code that runs.  Examples in class will be worked out in Python and Lisp (probably leaning more towards the Python).  Sample code for many of the algorithms discussed in the text is provided in a variety of languages (Python and Lisp, plus Java, C++, and C#).  You will be allowed to complete assignments using the language of your choice, and you will be welcome to use the reference code as a basis for your own experiments and extensions,

The textbook, as noted above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).''

The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include:

* search
* game-playing, including adversarial and stochastic search
* reinforcement learning, including value iteration and q-learning
* probabilistic reasoning, including hidden Markov models

!!Grading

There are three major categories of work that will be assessed.  These are:

* '''Weekly (or semi-weekly) assignments, 25%.'''  It is my opinion that the primary way to really learn new material is by working through assignments.  Assignments will be accepted up to one week late with a 25% reduction in that assignment's value.  ''If you fall behind on your homework, it is much better to cut your losses and work on the current assignment, instead of running behind trying to catch up.''

* '''Daily reading reports and brief presentations, 10%.''' We will be reading the Minsky book at the rate of approx. 7 sections chapters per class meeting.  (Each section is exactly one page in length.)  Each of you will prepare 140-character synopses of each section, assigned at each class and due on the next one.  Each day, I will randomly call on a person to lead a short discussion the assigned material.  Please have your synopses at hand for each class meeting; you may start the discussion by reading them.  You can expect to lead about twice over the course of the semester.  Please be prepared.

* '''Quizzes and a final exam, 30%.''' There will be two in-class quizzes during the semester. There will be a cumulative final, worth 20% of your overall grade.

* '''Term project, 30%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.

->In the final project, you will apply the ideas developed in the class in an original software implementation. You may thus connect the ideas of the class with your own interests&#151;music, robotics, art, databases, the web, networking, gaming, etc. The learning goal of the project is to have you find some real-world relevance of the ideas in the class.

Classroom participation is worth 5% of your overall grade.  In practice, if your other grades put you on a marking boundary, this will push it one way or the other.

To summarize:

25% Weekly homeworks \\
10% Minsky reports \\
10% Two quizzes \\
20% Final \\
30% Project \\
5% Classroom participation \\

!!Discussion Group / E-Mail List

We will use Google Groups for class conversation and announcements.  Please join this group.  I'd advise setting your preferences to immediate, individual delivery of messages&#151;click the &#147;Edit my membership&#148; tab.

(:html:)
<table style="border:1px solid #aa0033; font-size:small" align=center>
  <tr>
    <td rowspan=3>
    <img src="http://groups.google.com/groups/img/groups_medium.gif" height=58 width=150 alt="Google Groups">
    </td>
    <td colspan=2 align=center><b>Subscribe to uml-ai-fall12</b></td>
  </tr>
  <form action="http://groups.google.com/group/uml-ai-fall12/boxsubscribe">
  <tr>
    <td>Email: <input type=text name=email></td>
    <td>
      <table
      style="background-color:#ffcc33;padding:2px;border:2px outset #ffcc33;">
      <tr>
        <td>
        <input type=submit name="sub" value="Request">
        </td>
      </tr>
      </table>
    </td>
  </tr>
  </form>
  <tr><td colspan=2 align=center>
  <a href="http://groups.google.com/group/uml-ai-fall12" target="new">Browse Archives</a>
  </td></tr>
</table>
(:htmlend:)

The group address is mailto:uml-ai-fall12@googlegroups.com.  You have to be a member to send to the list.

!!Undergraduate Project Sequence

For undergraduates, 91.420 Artificial Intelligence can be grouped with 91.421 Machine Learning ''or'' 91.450 Robotics I to form a course pair.

!!Graduate Group

For graduate students, 91.543 is in Group IV, &#147;Information Management and Analysis.&#148;

!!Collaboration Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.  Please be familiar with the university's academic integrity policy [[for undergraduates->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]] or [[for graduate students->http://www.uml.edu/catalog/graduate/policies/academic_dishonesty.htm]].
Changed line 22 from:
The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
to:
The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. ''New and used copies are available at the UML bookstore.''  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.
Changed line 24 from:
We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).''
to:
We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).
Deleted line 0:
Changed line 5 from:
TA:  '''tba'''
to:
TA:  ''tba'' \\
Added lines 1-106:

[[AIfall12|Home]] [[Assignments]] [[Lecture Blog]] [[Resources]] [[Project]] [[http://groups.google.com/group/uml-ai-fall12 | Discussion Group]]

91.420/91.543 Artificial Intelligence, Fall 2012 \\
'''Prof. Fred Martin''', (:html:)<a href="http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=" onclick="window.open('http://mailhide.recaptcha.net/d?k=01COSqrfJ-58cc94fQb2pI1A==&c=iZBP8kCznrjdnfw8QFFKADFtsIimnLdVHk581djoISQ=', '', 'toolbar=0,scrollbars=0,location=0,statusbar=0, menubar=0,resizable=0,width=500,height=300'); return false;" title="Reveal this e-mail address">click for fred's email</a>(:htmlend:) \\
TA:  '''tba'''
Tue/ThuMon/Wed/Fri, 12:30p&#150;1:45p, OS403

We will be using the following books:

|| border=0 width=100% cellpadding=10
|| '''Artificial Intelligence: A Modern Approach''' (3rd edition &#150; 2009) [[<<]] Stuart Russell and Peter Norvig  [[<<]] %height=150px% [[http://aima.cs.berkeley.edu/ | Attach:aima-cover.jpg]] || '''The Society of Mind''' (1987) [[<<]] Marvin Minsky [[<<]] %height=150px% [[http://web.media.mit.edu/~minsky/ | Attach:som-minsky.jpg]]
|| By far the best AI text. || &#147;The mind is what the brain does.&#148;&#151;Steven Pinker

!!What is AI?

There are few areas in computer science as broad as artificial intelligence.  AI encompasses algorithm design, agents and robots, natural language understanding, expert systems, music and sound, as well as philosophical questions about the nature of consciousness!

In this class, we will focus on the practical.  The goal will be to illustrate all ideas with code that runs.  Examples in class will be worked out in Python and Lisp (probably leaning more towards the Python).  Sample code for many of the algorithms discussed in the text is provided in a variety of languages (Python and Lisp, plus Java, C++, and C#).  You will be allowed to complete assignments using the language of your choice, and you will be welcome to use the reference code as a basis for your own experiments and extensions,

The textbook, as noted above, is ''Artificial Intelligence: A Modern Approach,'' by Russell and Norvig.  The book is comprehensive, is well-written in the most exemplary manner, and has detailed bibliographies for each chapter.  It is by far the most popular book used to teach AI, and it is also the best.

The authors have recently published the third edition of &#147;AIMA.&#148;  I do recommend this new edition. New and used copies are available at the UML bookstore.  It would be acceptable to get a used second edition; these are typically available for $25 to $35 plus shipping (''[[alibris->http://www.alibris.com/booksearch?qisbn=9780137903955]]; [[amazon->http://www.amazon.com/Artificial-Intelligence-Modern-Approach-2nd/dp/0137903952/]]; [[bookfinder->http://www.bookfinder.com/search/?author=&title=&lang=en&isbn=0137903952&submit=Begin+search&new_used=*&destination=us&currency=USD&mode=basic&st=sr&ac=qr]]'').  Please do not use the first edition.

We will also have readings and discussions based on Marvin Minsky's seminal ''The Society of Mind''.  Minsky is often considered the &#147;father of AI,&#148; and this work lays the foundation for &#147;strong AI&#148;&#151;the idea that AI could ultimately produce truly intelligent synthetic brains, not merely systems that appear to act in intelligent ways.  ''Minsky&#146;s book is also available at the UML bookstore,'' or you may purchase a used copy ([[alibris->http://www.alibris.com/booksearch?qisbn=9780671657130]]; [[amazon->http://www.amazon.com/Society-Mind-Marvin-Minsky/dp/0671607405/]]).''

The bulk of our work will focus on more mundane matters, and the content in AIMA could easily fill two semesters and still be considered an introduction.  As such, we will not attempt to cover every topic, but rather to learn a good subset of topics well.  The agenda for the semester will include:

* search
* game-playing, including adversarial and stochastic search
* reinforcement learning, including value iteration and q-learning
* probabilistic reasoning, including hidden Markov models

!!Grading

There are three major categories of work that will be assessed.  These are:

* '''Weekly (or semi-weekly) assignments, 25%.'''  It is my opinion that the primary way to really learn new material is by working through assignments.  Assignments will be accepted up to one week late with a 25% reduction in that assignment's value.  ''If you fall behind on your homework, it is much better to cut your losses and work on the current assignment, instead of running behind trying to catch up.''

* '''Daily reading reports and brief presentations, 10%.''' We will be reading the Minsky book at the rate of approx. 7 sections chapters per class meeting.  (Each section is exactly one page in length.)  Each of you will prepare 140-character synopses of each section, assigned at each class and due on the next one.  Each day, I will randomly call on a person to lead a short discussion the assigned material.  Please have your synopses at hand for each class meeting; you may start the discussion by reading them.  You can expect to lead about twice over the course of the semester.  Please be prepared.

* '''Quizzes and a final exam, 30%.''' There will be two in-class quizzes during the semester. There will be a cumulative final, worth 20% of your overall grade.

* '''Term project, 30%.''' A significant part of the class will be an independent implementation project, which you will specify and carry out, primarily over the last month of the semester.  We'll start conceptual work on the project earlier than that.  I will expect the project to represent a significant work effort, and I will assist you in organizing your time so that this happens.

->In the final project, you will apply the ideas developed in the class in an original software implementation. You may thus connect the ideas of the class with your own interests&#151;music, robotics, art, databases, the web, networking, gaming, etc. The learning goal of the project is to have you find some real-world relevance of the ideas in the class.

Classroom participation is worth 5% of your overall grade.  In practice, if your other grades put you on a marking boundary, this will push it one way or the other.

To summarize:

25% Weekly homeworks \\
10% Minsky reports \\
10% Two quizzes \\
20% Final \\
30% Project \\
5% Classroom participation \\

!!Discussion Group / E-Mail List

We will use Google Groups for class conversation and announcements.  Please join this group.  I'd advise setting your preferences to immediate, individual delivery of messages&#151;click the &#147;Edit my membership&#148; tab.

(:html:)
<table style="border:1px solid #aa0033; font-size:small" align=center>
  <tr>
    <td rowspan=3>
    <img src="http://groups.google.com/groups/img/groups_medium.gif" height=58 width=150 alt="Google Groups">
    </td>
    <td colspan=2 align=center><b>Subscribe to uml-ai-fall12</b></td>
  </tr>
  <form action="http://groups.google.com/group/uml-ai-fall12/boxsubscribe">
  <tr>
    <td>Email: <input type=text name=email></td>
    <td>
      <table
      style="background-color:#ffcc33;padding:2px;border:2px outset #ffcc33;">
      <tr>
        <td>
        <input type=submit name="sub" value="Request">
        </td>
      </tr>
      </table>
    </td>
  </tr>
  </form>
  <tr><td colspan=2 align=center>
  <a href="http://groups.google.com/group/uml-ai-fall12" target="new">Browse Archives</a>
  </td></tr>
</table>
(:htmlend:)

The group address is mailto:uml-ai-fall12@googlegroups.com.  You have to be a member to send to the list.

!!Project Sequence

For undergraduates, 91.420 Artificial Intelligence can be grouped with 91.450 Robotics I to form a course pair.


!!Collaboration Policy

You are welcome to discuss ideas in the class with your peers.  However, pair programming or other side-by-side work that involves sharing of code is not allowed.  By turning in an assignment, you attest that ''you have written'' the new code that it includes.  Please be familiar with the university's [[academic integrity policy->http://www.uml.edu/catalog/undergraduate/policies/academic_dishonesty.htm]].

!!Graduate Section

The graduate section is 91.543.201.  In addition to being treated as honors students, students who are registered in the graduate section will locate, read, and report on current and/or historical research papers associated with each of the topics in the class.  Also, you will prepare a paper of your own, based on your implementation project.

Edit - History - Print - Recent Changes - Search
Page last modified on December 03, 2012, at 08:59 PM