COMP SCI 3016 - Computational Cognitive Science

North Terrace Campus - Semester 1 - 2014

This course provides an introduction to computational theories of human cognition. We use formal models from artificial intelligence and mathematical psychology to consider fundamental issues in human knowledge representation, inductive reasoning, learning, decision-making and language acquisition. What kind of informational structures describe the organisation of human knowledge, and what kinds of inferences do they license? How do humans make choices given time constraints, computational limitations, and external costs imposed by the world? What kinds of innate knowledge (if any) must people have? And how can formal models of human cognition inform our understanding of the design of intelligent machines? Representative modelling techniques include stochastic processes, Bayesian models, formal grammars, and random graph models.

  • General Course Information
    Course Details
    Course Code COMP SCI 3016
    Course Computational Cognitive Science
    Coordinating Unit Computer Science
    Term Semester 1
    Level Undergraduate
    Location/s North Terrace Campus
    Units 3
    Contact Up to 3 hours per week
    Prerequisites One of COMP SCI 1007, COMP SCI 1009, COMP SCI 1103, COMP SCI 1203, COMP SCI 2103 or COMP SCI 2202 & one of APP MTH 1000 or COMP SCI 1012
    Assumed Knowledge Basic probability as taught in MATHS 2103 & some familiarity with programming in MATLAB
    Course Description This course provides an introduction to computational theories of human cognition. We use formal models from artificial intelligence and mathematical psychology to consider fundamental issues in human knowledge representation, inductive reasoning, learning, decision-making and language acquisition. What kind of informational structures describe the organisation of human knowledge, and what kinds of inferences do they license? How do humans make choices given time constraints, computational limitations, and external costs imposed by the world? What kinds of innate knowledge (if any) must people have? And how can formal models of human cognition inform our understanding of the design of intelligent machines? Representative modelling techniques include stochastic processes, Bayesian models, formal grammars, and random graph models.
    Course Staff

    Course Coordinator: Dr Amy Perfors

    Lecturer: Dan Navarro.  daniel.navarro@adelaide.edu.au

    Course Timetable

    The full timetable of all activities for this course can be accessed from Course Planner.

  • Learning Outcomes
    Course Learning Outcomes
    1. An understanding of how machine learning and human learning are connected.
    2. An understanding of some of the main questions in cognitive science, an ability to identify the important issues, and comprehend the empirical data that bear on them.
    3. Experience in understanding psychological ideas and translating psychological theories to computational or mathematical models.
    4. Understanding how to apply computational models and algorithms to cognitive science data, and to understand how and to what problems these models apply.
    5. Knowledge of how computational and mathematical theories can apply to real-world problems, and be used to effectively find solutions.
    6. To develop communication skills and the ability to work on a novel project involving analysis and write-up of the results.
    University Graduate Attributes

    This course will provide students with an opportunity to develop the Graduate Attribute(s) specified below:

    University Graduate Attribute Course Learning Outcome(s)
    Knowledge and understanding of the content and techniques of a chosen discipline at advanced levels that are internationally recognised. 1-5
    The ability to locate, analyse, evaluate and synthesise information from a wide variety of sources in a planned and timely manner. 5-6
    An ability to apply effective, creative and innovative solutions, both independently and cooperatively, to current and future problems. 4-6
    Skills of a high order in interpersonal understanding, teamwork and communication. 6
    A proficiency in the appropriate use of contemporary technologies. 1-5
    A commitment to continuous learning and the capacity to maintain intellectual curiosity throughout life. 1-2, 5
    A commitment to the highest standards of professional endeavour and the ability to take a leadership role in the community. 1-3
    An awareness of ethical, social and cultural issues within a global context and their importance in the exercise of professional skills and responsibilities. N/A
  • Learning Resources
    Required Resources
    There is no prescribed textbook for the course. Readings will be available from MyUni and consist of articles relevant to the models and theories considered. Problem sets will include small programming projects in R or similar language.
    Online Learning
    The Computational Cognitive Science course has a MyUni page, through which all course announcements and information will be posted. Additional resources are sometimes made available via the course website located at health.adelaide.edu.au/psychology/ccs/teaching/ccs
  • Learning & Teaching Activities
    Learning & Teaching Modes
    This course aims to introduce students to the fundamental issues in cognitive science to which computational models can provide insight, and to guide them in applying such models to human data. The concepts are taught initially via traditional lectures, and will be practised and reinforced by individual problem sets that involve both programming and problems solving, as well as a semester-long final project (which students can work on individually or in pairs) in which the students must either (a) apply a mathematical or computational model or (b) perform a short experiment in reference to a simple problem in cognitive science and provide a short write- up of the results.
    Workload

    The information below is provided as a guide to assist students in engaging appropriately with the course requirements.

    Computational Cognitive Science is a 3 unit course. The expectation is that students will be spending 12 hours per week working on the course. This will include 3 hours per week of lectures and 1 hour per week of required tutorial. There will be three short problem sets due over the course of the semester, and one final project which will involve a novel experiment, model, or mathematical analysis of the students’ choice, coupled with a short write-up of what was done
    Learning Activities Summary
    Week 1: Introduction and overview; Basic Bayesian inference
    Week 2: Inductive generalisations
    Week 3: Simple supervised classification
    Week 4: Semi-supervised and unsupervised classification
    Week 5: Higher order knowledge in classification
    Week 6: Structure in time and space
    Week 7: Sampling information from the world and helpful teachers
    Week 8: Sensitivity to the value of information
    Week 9: Information search and retrieval
    Week 10: Exploring and exploiting information in the world
    Week 11: Advanced computational statistics
    Week 12: Summary
  • Assessment

    The University's policy on Assessment for Coursework Programs is based on the following four principles:

    1. Assessment must encourage and reinforce learning.
    2. Assessment must enable robust and fair judgements about student performance.
    3. Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
    4. Assessment must maintain academic standards.

    Assessment Summary
    The assessment for this subject consists of four components with the following weightings:
    (a) Exam - 60%
    (b) Problem sets (three, at 7% each) - 21%
    (c) Final project - 15%
    (d) Tutorial attendance and participation - 4%

    The component consists of the following tasks: Task Task Type Due Date Weighting Learning objectives Exam Formative End of term 50% 1, 3, 4 Problem sets Formative 26/3, 28/4, 14/5 30% 2, 3, 4 Final project Formative 28/5 15% 1, 2, 3, 4, 5 Quiz Formative 12/3 5% 1

    Task Task type Due date Weighting Learning objectives
    Exam Formative End of term 60% 1, 2, 3, 4, 5
    Problem sets Formative 4/4, 9/5, 30/5 21% 1, 2, 3, 4, 5
    Final project Formative End of term 15% 2, 3, 4, 5, 6
    Tutorial participation Formative Throughout 4% 2, 5, 6
    Assessment Detail
    EXAM
    The exam will be a 3 hour open book exam. The exam will consist of questions that require the student to apply the models and techniques to interesting cognitive science problems, or to discuss how they would apply them. It will also consist of questions evaluating to what extent students understand the problems and the techniques.

    PROBLEM SETS
    There will be three problem sets, consisting of questions designed to (a) evaluate student understanding of the problems in cognitive science, the theories proposed to account for them, and the data that is relevant; and (b) evaluate student ability to program and understand computational and mathematical models relevant to those problems. Questions focusing on (a) will tend to be short-answer, while questions focusing on (b) will generally require some R programing and/or mathematical analysis.

    FINAL PROJECT
    Students will have the option of working on the final project either individually or in pairs. The final project must be of one of the following forms: (a) Research review (b)Project and small write-up. If students choose (a), their maximum score will be lower (90% out of 100%) since it is an easier option. It will consist of a 2000-3000 word report on a topic of their choice in cognitive science, to which computational or mathematical modeling has contributed. Projects will be assessed on their clarity, and understanding of the literature and technical details. If students choose (b), they will have to identify an interesting topic in cognitive science and either (i) implement a computational model; (ii) perform a mathematical analysis; or (iii) run a simple experiment relevant to that topic. They will then have to write up their project in a 1000-2500 word report. Projects will be assessed on clarity, correctness in implementation, and appropriateness for the question in cognitive science identified as relevant.

    TUTORIAL PARTICIPATION
    Student will receive a small amount credit for attending and actively participating in the tutorial exercises and discussions. 
    Submission
    Problem sets and the final project will be submitted via MyUni before the date they are due. Problem sets must be named as lastname-firstname-psetN where N is the number of the problem set; the final project must be named lastname-firstname-project; and any code attached to either of these should be named lastname-firstname-code-X where X is either psetN or project. Submitted text files must be in pdf format.

    If work is handed in late, the mark will be capped based on how many days late it is. Each subsequent weekday late will result in a 10% reduction in the final grade. (One weekday means that if a problem set was due on Friday and it is turned in on Monday, this will be a 10% reduction). There will be no leeway given on the due date; if an assignment is turned in at 12.05am on Saturday when it was due on 11.59pm on Friday, that will result in a full 10% deduction.
    Course Grading

    Grades for your performance in this course will be awarded in accordance with the following scheme:

    M10 (Coursework Mark Scheme)
    Grade Mark Description
    FNS   Fail No Submission
    F 1-49 Fail
    P 50-64 Pass
    C 65-74 Credit
    D 75-84 Distinction
    HD 85-100 High Distinction
    CN   Continuing
    NFE   No Formal Examination
    RP   Result Pending

    Further details of the grades/results can be obtained from Examinations.

    Grade Descriptors are available which provide a general guide to the standard of work that is expected at each grade level. More information at Assessment for Coursework Programs.

    Final results for this course will be made available through Access Adelaide.

  • Student Feedback

    The University places a high priority on approaches to learning and teaching that enhance the student experience. Feedback is sought from students in a variety of ways including on-going engagement with staff, the use of online discussion boards and the use of Student Experience of Learning and Teaching (SELT) surveys as well as GOS surveys and Program reviews.

    SELTs are an important source of information to inform individual teaching practice, decisions about teaching duties, and course and program curriculum design. They enable the University to assess how effectively its learning environments and teaching practices facilitate student engagement and learning outcomes. Under the current SELT Policy (http://www.adelaide.edu.au/policies/101/) course SELTs are mandated and must be conducted at the conclusion of each term/semester/trimester for every course offering. Feedback on issues raised through course SELT surveys is made available to enrolled students through various resources (e.g. MyUni). In addition aggregated course SELT data is available.

  • Student Support
  • Policies & Guidelines
  • Fraud Awareness

    Students are reminded that in order to maintain the academic integrity of all programs and courses, the university has a zero-tolerance approach to students offering money or significant value goods or services to any staff member who is involved in their teaching or assessment. Students offering lecturers or tutors or professional staff anything more than a small token of appreciation is totally unacceptable, in any circumstances. Staff members are obliged to report all such incidents to their supervisor/manager, who will refer them for action under the university's student’s disciplinary procedures.

The University of Adelaide is committed to regular reviews of the courses and programs it offers to students. The University of Adelaide therefore reserves the right to discontinue or vary programs and courses without notice. Please read the important information contained in the disclaimer.