CS B552 Knowledge-Based Artificial IntelligenceHomework 5: Project SketchDue Date: Group makeup due to Eriya via Canvas text submission by 11:59pm Wed, Mar 8; Sketch due 11:59pm, Friday, Mar 10.
Assignment Goals The goals of the assignment are (1) to identify your project topic and formulate initial plans for pursuing it, and (2) to give us information to enable our giving useful feedback to help ensure its success.
Collaboration and Project Groups You're strongly encouraged to discuss your plans and ideas with us and with any other students (whether or not in your project group, or even in the class!) before you submit your project plan. You don’t need to acknowledge these discussions in your writeup. You’re encouraged to form 2-person project groups. Individual projects are possible, as are 3-person projects if the task can be broken into three distinct components with clear division of responsibility. Only one writeup (sketch) is required per project group, and the writeup may be submitted by any student in the group (please be sure to include the names of all members in the group). The writeup should be 1-2 pages.
The Project Description The goal of the project is to give you a chance to do research on a topic of your choice---to critically examine an area, formulate interesting questions, creatively try to overcome problems, and analyze what you've learned from your work. In past classes, students have sometimes chosen to continue these projects beyond the class, and have even had their project work lead to research publications (in at least one case, the project topic carried over into a dissertation). Try to select a challenging topic that you care about, and don't be afraid to take risks. If you pick a challenging topic, there’ll be good lessons regardless of whether the outcome is exactly as you predicted. Each project must include a substantial implementation of a knowledge-based AI method, building on aspects of one of the methods/approaches/topics discussed in class (e.g., rule-based reasoning, knowledge representation and capture, conceptual analysis, script-based understanding, ontologies, memory organization, case-based reasoning) to address new issues or extend the approach. Each project should include some new ideas you’ve developed. It’s fine to use existing code to provide foundational functionality for your system, if properly acknowledged, to let you spend more time on your own implementation of the novel part of your work. Use of existing code does not decrease the amount of code to be developed by the project team. A substantial part of the project work must include a major software component which you have written (in any language you choose) and evaluation. There are both rich knowledge resources (e.g., OpenCyc, ConceptNet) and software resources (e.g., Montylingua, the AI microprograms, IUCBRF) available for use in your projects if you wish.
The Project Sketch The project sketch should include the following points (please include them in order and number them as below): 1) The names of the project group members 2) A concise title summarizing the issue(s) to be addressed in your project. 3) The overarching question that you are investigating/modeling, in a sentence or two. This should go beyond the task domain. 4) Why this problem is important to knowledge-based AI 5) Your goals for system performance, including the intended I/O behavior of the system (in some projects the user interface may be important, and in others it might not be) 6) The knowledge-based AI method(s) you intend to use 7) The task domain 8) For a group project, how you will divide up the task/implementation among the group members 9) How you will evaluate the project's success 10) What you expect to be the hardest/most interesting part 11) What you expect to demonstrate or learn from the project.
Grading criteria for the full project To help in your project design, please keep in mind that the following grading criteria will be used at the end of the semester for the projects themselves. If you're interested in a project that doesn't fit into all the aspects of this list, please talk to me in advance. Problem (25%) Is it interesting and challenging? Model and assessment (35%) Is the theoretical solution interesting? Would it scale up? Does it make theoretical claims? (E.g., saying something about needed knowledge for a task, or the strengths and weaknesses of a given process, or about what are the hard and easy parts of the problem you're attacking.) Is its performance well evaluated? Paper (20%) Writing Motivation Relation to other work Analysis of strengths+weaknesses Clarity on program (All major points should be described, but at a fairly high level) Program (20%) A well-documented implementation of model.
Please let us know if you have any questions! Submission The project sketch will be submitted electronically, on Canvas. Only one student per group should submit. Be sure to include all group members’ names on each submission. |