CS 630: Cognitive Systems

Course Syllabus

Professor: Dario Salvucci
Email: salvucci @ cs.drexel.edu
Office: University Crossings 142
Office Hours: Tuesday 11-12 or email for appointment

Description

This course explores the principles of cognition and intelligence in humans and machines, focusing on how to build computational models that, in essence, think and act like people. In the course we will (1) review existing frameworks for modeling human cognition, including broad categories of symbolic, connectionist, and hybrid frameworks; (2) study a particular framework in the context of illustrative psychological domains (e.g., memory, attention, language); (3) build running simulation models of cognition and performance using this framework; and (4) explore how such models can be employed in real-world application domains such as intelligent tutoring and driving.

Prerequisites

This course has no specific course prerequisites. However, students should have a solid foundation in programming concepts and algorithms. Experience with the LISP programming language will be helpful, but students unfamiliar with LISP can likely pick up the necessary skills through lectures and readings.

Classes

Class time will generally be include both a lecture with new material and a laboratory component with hands-on practice designing and building models. Topics covered in class will include the following (in rough chronological order):

Readings

There is no assigned textbook for this course. Readings will come from several sources including academic papers and electronic resources (e.g., web tutorials). We expect that you will complete the assigned readings before the start of lecture so that we can enjoy more fruitful discussions.

Assignments

Homework assignments will include writing papers on class topics, designing high-level models, and building and testing actual simulation models. For the simulation models, we will utilize the ACT-R framework which is implemented in the LISP programming language. While some LISP experience may be helpful, ACT-R models have their own particular syntax which will be taught in class; thus, there will be little actual LISP programming in the course.

Grading

All aspects of this course are important for developing an understanding of and appreciation for cognitive systems and modeling. The bulk of the grade comes from the homework assignments, but class participation is also heavily considered in your grade. The grading breakdown will be as follows: Late assignments will not be accepted and receive a score of 0.

Communication

The instructor will disseminate important announcements by email through the course mailing list, and also post these announcements on the course web site. Also, the web site contains a timeline with links to all information (lecture slides, assignments, etc.) relevant to the course.

Policies

Attendance for lectures and exams is expected. In the case of a school closing on an exam day, the exam will be given in the next class period. The Drexel snow emergency information number is (215) 895-6358.

Academic honesty is essential. Cheating, academic misconduct, plagiarism, and fabrication of any submitted material, including both code and prose, are serious breaches of academic integrity and will be dealt with accordingly. Violations will result minimally in a grade of zero for the exam/assignment in question, an additional reduction of one letter grade in the overall course grade, and a report of the violation to the Drexel administration; further penalties may apply to more serious and/or repeat violations. Please refer to Drexel's official Academic Honesty Policy for more information.