CS 5973: Neuro/Cognitive Robotics Syllabus

General Information

Meeting time: Tu/Th 3:00-4:15
Location: Carson 438
Prerequisites: none. However, I will assume a graduate-level background in one of the related areas (computer science or engineering, cognitive psychology, or neuroscience). In addition I will assume introductory-level training in probability and statistics.
Course web page: http://www.cs.ou.edu/~fagg/classes/neurocog
We will also be making heavy use of the course blackboard at learn.ou.edu
Instructor: Dr. Andrew H. Fagg
- Office: EL 152
- Phone: 325-8606
- Homepage: http://www.cs.ou.edu/~fagg
- Email: fagg [[at]] ou.edu
- Office hours: T/Th 2:00-3:00

Course Goals and Topics

The goals of this course include:

Understand how biological systems (primates, in particular) perform cognitive and motor tasks. We will examine cognitive science and neuroscience theories that attempt to answer the following:
- What representations/abstractions of the environment are used?
- How are motor skills represented?
- How can these representations be acquired?
- How is conceptual knowledge grounded in the real world?
Understand how these theories can be couched in a computational framework
Evaluate specific robotic implementations of these theories in order to understand:
- how to approach robot control in general, and
- what these implementations say about the biological implementations.

Topics will include:

The representation and learning of sequential motor skill (with particular focus on visual attention, reaching, grasping, and manipulation)
Action-oriented visual processing: the "how" and "what" visual pathways and their relationship to "affordances"
The use of affordances in the perception of the actions made by other agents
Symbol grounding and proto-language learning through perception and through interaction with the environment
The direct interface between brain and robot
Agent-agent interaction in learning and collaboration

Grades

Final grades will be computed according to the following distribution:

Class participation (including leading discussions): 35%
Paper summaries: 20%
Project proposal: 5%
Project status report 1: 5%
Project status report 2: 5%
Paper draft: 10%
Final project presentation: 10%
Final paper: 10%

Grade questions: Grading questions may be brought to me at any time during the semester. Please note that I will examine the entire project or paper summary in question and your final grade may end up lower.
learn.ou.edu: The blackboard has a grade book that is used to store the raw data that is used to calculate your course grade. It is the responsibility of each student in this class to check their grades on the blackboard after each project or homework is returned. If an error is found, bring the graded document to me and we will correct the record.

Paper Discussion Leaders

We will be reading on the order of 40 papers through the course of the semester. Everyone is responsible for reading these papers. However, one student will be designated for each paper as the discussion leader. This leader is responsible for having read the paper thoroughly and for putting together an electronic presentation that he/she will use in class. This presentation should address the following:

What is (are) the hypothesis (hypotheses)?
What are the essential components of the experiment?
What are the results? Do the results support the paper's hypothesis? How well?
What new questions does the paper raise?
How does this paper relate to others (either that we have read as a group or that you have read on your own)?

Note that the discussion leader does not have to have all of the answers (i.e., it is fine to say "I really didn't understand *this*, let's understand it as a group").

Each student should expect to lead the discussion for five papers during the semester.

Paper Summaries

In order to ensure that everyone is keeping up with the readings, I will be collecting one-paragraph summaries of each paper that we discuss in class. These summaries should include a discussion of the key computational points, the experimental approach, and an evaluation of the experimental results. These summaries must be handed in prior to the first class in which we discuss the paper (email is preferred). In order to receive full credit for paper summaries, each student must hand in a total of 30 summaries during the semester; these summaries must be on the papers for which the student did not act as a discussion leader.

Semester Project

The semester-long project constitutes a significant percentage of your class grade. Projects will be experimental in nature, requiring a carefully-designed computational hypothesis, a computer implementation, an experiment, and an analysis of the results. Project topics must be based on a set of at least three papers drawn from the literature; one of these papers must be drawn from the set of papers on the course schedule page. With approval, students may collaborate on projects in groups of size two. In these projects, it must be clear that there is a significant and differentiable contribution that can be made by each student.

A set of project ideas will be made available within the first couple of weeks of the semester.

For those students who do not have a significant background in programming, we will make every effort to design an appropriate collaborative project.

All project-related materials must be handed in on the specified due date: for in-class presentations, you must be ready to present in class; written materials are due at 23:59. Written materials may be handed in via email or the course blackboard.

Key Deadlines

Sept 15: 1-page project proposal due
Sept 20: In-class presentation of project proposal
Oct 18: In-class presentation of project status
Nov 8: In-class presentation of project status
Nov 15: Draft of final paper due
Nov 22: Peer paper reviews due
Dec 6: Final paper due
Dec 8: Final project presentations
Final period (date TBD): project presentations

Note that any material may be handed in at any time prior to the deadline.

Course Policies

Attendance: Class time will largely be dedicated to the discussion (and, hopefully, mutual understanding) of the reading material. This is especially the case given that everyone is coming into the class with different backgrounds. Attendance is therefore absolutely critical to the success of the class and to your success in the class.
Class Web Page: Most of the material that you will need can be found on the class web page located at: http://www.cs.ou.edu/~fagg/classes/neurocog/
Class Blackboard: This class will also use the blackboard software, located at: http://learn.ou.edu/d2l/orgTools/ouHome/ouHome.asp?ou=39371 Login with your 4+4 (usually the first four letters of your last name followed by the last four digits of your student number), using your standard OU password. If you have difficulty logging in, call 325-HELP. This software provides a number of useful features, including a list of announcements, an electronic mailing list, newsgroups, and grade book.
I will update the main web site and the blackboard page several times a week. When I update the site in any significant way, I will post an announcement on the blackboard telling you what has been added and where it is located. You are responsible for things posted on the site within 48 hours of the post.
Class Email Alias: Urgent announcements will be sent through email. It is your responsibility to:
- Have your university supplied email account properly forwarded to the location where you read email.
- Make sure that your email address in learn.ou.edu is correct, and forwards email to the place where you read it. I'll send out a test message during the first week of class. If you do not receive this message, it is your responsibility to get the problem resolved immediately.
- Have your email program set up properly so that replying to your email will work correctly the first time. You can send email to yourself and reply to yourself to test this. I will not make any attempt to get bounced email messages delivered.
If you need assistance in accomplishing any of these tasks, contact 325-HELP.
Examinations: There will not be any exams in this class. The final exam period will be used for some of our final project reports.
Projects: a significant component of your final grade will be based on your performance for the semester-long project. Collaborative projects (no more than 2 students) will be allowed if I can be convinced that there can be a significant, differentiable contribution by each of the students.
Newsgroups and Email: The newsgroup on learn.ou.edu should be the primary method of communication (outside of class). This allows everyone in the class to benefit from the answer to your question, and provides students with more timely answers since I check the blackboard at least once a day. Matters of personal interest should be directed to email instead of to the newsgroup, e.g. informing me of an extended personal illness.
Academic Misconduct: Feel free to discuss papers and projects with other members of the class or myself. However, do not copy another student's work, as this is considered cheating. If you have been approved for a collaborative project, then project-related materials may be shared.
You may make use of the net as a reference as you are working on paper summaries and projects. However, downloading specific solutions or wording from the net is also considered cheating. Making use of net-available libraries (e.g., for basic mathematical or image processing functionality) must be approved. When in doubt -- ask.
Upon the first documented occurrence of cheating, I will report the academic misconduct to the Campus Judicial Coordinator. The procedure to be followed is documented in the University of Oklahoma Academic Misconduct Code ( http://www.ou.edu/studentcode/OUStudentCode.pdf). In the unlikely event that I elect to admonish the student, the appeals process is described in http://www.ou.edu/provost/integrity-rights/.
Incompletes: The grade of "I" is intended for the rare circumstance when a student who has been successful in a class has an unexpected event occur shortly before the end of the class. I will not consider giving a student a grade of "I" unless the following three conditions have been met.
- It is within two weeks of the end of the semester.
- The student has a grade of C or better in the class.
- The reason that the student cannot complete the class is properly documented and compelling.
Accommodation of Disabilities: The University of Oklahoma is committed to providing reasonable accommodation for all students with disabilities. Students with disabilities who require accommodations in this course are requested to speak with the professor as early in the semester as possible. Students with disabilities must be registered with the Office of Disability Services prior to receiving accommodations in this course. The Office of Disability Services is located in Goddard Health Center, Suite 166, phone 405/325-3852 or TDD only 405/325-4173.

fagg [[at]] ou.edu

Last modified: Thu Sep 8 13:25:35 2005