Introduction to Artificial Intelligence: CSCI 3202

 

Course Instructor: Greg Grudic

 

 

Class Location:

TR 12:30-1:45  ECCR 105

My Office:

ECOT 525

Office Hours:

Wednesdays10:00 to 11:00. Thursdays 2:00 to 3:00.

And By Appointment.

Phone:

303-492-4419

Email:

grudic@cs.colorado.edu

Course URL:

http://www.cs.colorado.edu/~grudic/teaching/CSCI3202_2007

 

 

 

This course will focus on developing a practical understanding of the fundamentals of Artificial Intelligence. The main focus of the course will be a group project, which will involve putting together a complete Artificial Intelligent Robotic System. The students will work in groups of 4 or 5 and will implement the complete sensing, computation and action capabilities required for a state of the art Robotic system. The task of the robotic system will be to explore the environment using computer vision, and to build maps that allow it to get from any initial to final position in any environment. Therefore, Sensing will be implemented using Computer Vision, Computation will be implemented using Reasoning, Planning, Machine Learning, and Optimal Decision Theory, and Actuation will be implemented by taking the results of the Computations done and controlling the wheels of the robot in order to execute them.

 

There will be a robot competition between groups in the final two weeks of the course.

 

A video of the robot platform which will be used by the groups can be seen at http://ia.cs.colorado.edu/projects/lagr/videos/autonomous_demo.mov

 

A picture of the robot platfor is given below:

 

IMG_6515

 

 

Grading:

    Group Project                        60%

    Homework Assignments       30%

    Class Participation                10%

(There will be no final exam)

 

Mark Breakdown:

A   :    ≥ 90%

A-  :   ≥ 85%, < 90%

B+ :   ≥ 80%, < 85%

B   :   ≥ 75%, < 80%

B-  :   ≥ 70%, < 75%

C+ :   ≥ 65%, < 70%

C   :   ≥ 60%, < 65%

C-  :   ≥ 55%, < 60%

D   :   ≥ 50%, < 55%

F   :   < 50%

 

 

Homework:

 

1.     Homework 1: Due Thursday September 20 (11:59PM). (HW1.zip). Worth 3% of final your mark.

2.     Homework 2: Due Thursday October 2 (11:50PM). (HW2.zip). Worth 9% of final your mark.

3.     Homework 3: Due Thursday December 6 (11:55PM). (HW3_Ver_2_Code_Template.zip). Worth 13% of final your mark.

4.     Homework 4: Due Friday December 14 (11:55PM). Hand in answers to all quizzes. Worth 5% of final your mark.

 

 

Project info:

 

1.     Test 1: Assigned Thursday October 4, 2007. Code due Tuesday October 23, 2007. Test week is October 24 to 26, 2007. (Project_Part_1.ppt) (Project_Part_1.pdf). (tst1_code.zip). (Project_Test1.pdf).

2.     Test 2: Real time traversable parts of image labeling. Image Feature Selection (Project_Test2.pdf). (code) Assigned Thursday November 8, 2007. Code due 9:00 AM, Monday, December 3. Test week is December 3 to 7, 2007.

3.     Test 3: Planning robot paths. Assigned Thursday November 15, 2007. Code due 9:00 AM, Monday December 10, 2007. Test week is December 10 to 14, 2007. (astar_test_files.zip)

4.     Interview with Instructor: In class during week of December 10 to 14, 2007.

 

 

 

Quizzes:

 

1.     Quiz 2: (quiz2.pdf)

2.     Quiz 3: (quiz3.pdf)

 

Lectures:

 

1.     Tuesday, August 28, 2007: (Intro_1.ppt). (Intro_1.pdf).

2.     Thursday, August 30, 2007: (Intro_2.ppt). (Intro_2.pdf).

3.     Tuesday, September 4, 2007: (Intro_3.ppt). (Intro_3.pdf).

4.     Thursday, September 6, 2007: Introduction to Classification 1 (Class_Intro_1.ppt) (Class_Intro_1.pdf).

5.     Tuesday, September 11, 2007: The Goal of Classification (Goal_of_Classification_1.ppt) (Goal_of_Classification_1.pdf).

6.     Thursday, September 13, 2007: Perceptron Algorithm (Perceptron.ppt) (Perceptron.pdf).

7.     Tuesday, September 18, 2007: Perceptron Algorithm (Perceptron.ppt) (Perceptron.pdf).

8.     Thursday, September 20, 2007: Support Vector Classification 1 (SMV_classification_1.ppt)( SMV_classification_1.pdf).

9.     Tuesday, September 25, 2007: Support Vector Classification 2 (SMV_classification_2.ppt)( SMV_classification_2.pdf).

10.                         Thursday, September 27, 2007: Support Vector Classification 3 (SMV_classification_2.ppt)( SMV_classification_2.pdf).

11.                         Tuesday, October 2, 2007: Support Vector Classification Experiments.

12.                         Thursday, October 4, 2007: Class project, test 1, posted

13.                         Tuesday, October 9, 2007: Class Project discussion. K Nearest Neighbor Algorithm (NearestNeighbor.ppt) (NearestNeighbor.pdf).

14.                         Thursday, October 11, 2007: Computer Vision 1. (VisOverView.pdf)

15.                         Tuesday, October 16, 2007: Computer Vision 2. (MultiView3D.pdf)

16.                         Thursday, October 18, 2007: Model Selection and Future Error Prediction. (Model_Selection_Error_Prediction.pdf)

17.                         Tuesday, October 23, 2007: Model Selection and Future Error Prediction. (Model_Selection_Error_Prediction.pdf)

18.                         Thursday, October 25, 2007: Decision Tress. (Trees.pdf) (Trees.ppt)

19.                         Tuesday, October 30, 2007: Ensemble Learning. (Approaches_To_Supervised_Learning.pdf) (Approaches_To_Supervised_Learning.ppt)

20.                         Thursday, November 1, 2007: Ensemble Learning. (Approaches_To_Supervised_Learning.pdf) (Approaches_To_Supervised_Learning.ppt)

21.                         Tuesday, November 6, 2007: Homework 3 description.

22.                         Thursday, November 8, 2007: Project Part 2 description.

23.                         Tuesday, November 13, 2007: Search in AI 1. (Search Methods.pdf)

24.                         Thursday, November 15, 2007: Search in AI 2. (Search Methods.pdf)

25.                         Tuesday, November 20, 2007: Thanksgiving Break.

26.                         Thursday, November 22, 2007: Thanksgiving Break.

27.                         Tuesday, November 27, 2007: Search in AI 3. Project Part 3 description. (Search Methods.pdf)

28.                         Thursday, November 29, 2007: Optimal Decision Making Under Uncertainty.

29.                         Tuesday, December 4, 2007: Bayesian AI.

30.                         Thursday, December 6, 2007: Bayesian AI.

31.                         Tuesday, December 11, 2007: Group Meetings with Instructor.

32.                         Thursday, December 13, 2007: Group Meetings with Instructor.

 

 

 

 

 

 

 

 

 

Please note the following standard Policies of the University of Colorado:

 

“If you qualify for accommodations because of a disability, please submit to me a letter from Disability Services in a timely manner so that your needs may be addressed.  Disability Services determines accommodations based on documented disabilities.  Contact: 303-492-8671, Willard 322, and  http://www.Colorado.EDU/disabilityservices.”

 

Disability Services' letters for students with disabilities indicate legally mandated reasonable accommodations.  The syllabus statements and answers to Frequently Asked Questions can be found at http://www.colorado.edu/disabilityservices

 

"Campus policy regarding religious observances requires that faculty make every effort to reasonably and fairly deal with all students who, because of religious obligations, have conflicts with scheduled exams, assignments or required attendance.  In this class, {{insert your procedures here}} See full details at http://www.colorado.edu/policies/fac_relig.html"

 

"Students and faculty each have responsibility for maintaining an appropriate learning environment. Those who fail to adhere to such behavioral standards may be subject to discipline. Professional courtesy and sensitivity are especially important with respect to individuals and topics dealing with differences of race, culture, religion, politics, sexual orientation, gender, gender variance, and nationalities.  Class rosters are provided to the instructor with the student's legal name. I will gladly honor your request to address you by an alternate name or gender pronoun. Please advise me of this preference early in the semester so that I may make appropriate changes to my records.  See polices at

http://www.colorado.edu/policies/classbehavior.html   and at

http://www.colorado.edu/studentaffairs/judicialaffairs/code.html#student_code "

 

"The University of Colorado at Boulder policy on Discrimination and Harassment, the University of Colorado policy on Sexual Harassment and the University of Colorado policy on Amorous Relationships apply to all students, staff and faculty.  Any student, staff or faculty member who believes s/he has been the subject of discrimination or harassment based upon race, color, national origin, sex, age, disability, religion, sexual orientation, or veteran status should contact the Office of Discrimination and Harassment (ODH) at

303-492-2127 or the Office of Judicial Affairs at 303-492-5550.  Information about the ODH, the above referenced policies and the campus resources available to assist individuals regarding discrimination or harassment can be obtained at http://www.colorado.edu/odh "

 

"All students of the University of Colorado at Boulder are responsible for knowing and adhering to the academic integrity policy of this institution.

Violations of this policy may include: cheating, plagiarism, aid of academic dishonesty, fabrication, lying, bribery, and threatening behavior.  All incidents of academic misconduct shall be reported to the Honor Code Council (honor@colorado.edu; 303-725-2273). Students who are found to be in violation of the academic integrity policy will be subject to both academic sanctions from the faculty member and non-academic sanctions (including but not limited to university probation, suspension, or expulsion). Other information on the Honor Code can be found at http://www.colorado.edu/policies/honor.html  and at http://www.colorado.edu/academics/honorcode/ "