RIT Department of Computer Science

Description

Course Outcomes/Objectives

• Students will be able to describe attributes of various metaheuristic search procedures, their connections to informed search, and the situations to which they are well-suited. Evaluation: written assignments, class participation.
• Students will be able to implement, compare, and report on a variety of algorithms for search/optimization (evolutionary-based and swarm-based methods) and information processing (which includes both classical and modern approaches to biologically-motivated models for inference and learning in artificial neural systems). Evaluation: written assignments, research paper, research project.
• Students will be able to discuss the history and implications of biologially-inspired models and algorithms for optimization and information processing. Evaluation: written assignments, class participation.
• Students will be able to describe and discuss how humans perceive their world and process information. Evaluation: written assignments.
• Students will be able to synthesize research papers, present new material (orally/writing), and conduct a team project on biologically-inspired search and/or information processing. Evaluation: oral presentations, research paper, research project.

Instructor Contact

Grader Information

Lectures:

• Tues/Thurs 3:30-4:45pm, Slaughter Hall (SLA)-2150

Course Policies

• All homework in this course, other than the research report and presentation, is to be done on your own. You may discuss the homeworks in the general sense with your classmates, tutors, and the instructor. That is, no pictures for later, no shared notes, no shared code.
  Discussions with anybody else, including looking up the solutions online or in the literature other than the course book, are not permitted.
  You are encouraged to discuss any class material and homeworks whose deadline has passed with your peers, in the tutoring center, with the instructor, or anybody else whom you might make listen.
• The research project/report will be done in groups of 2 or 3 students - for this work, you may talk to other people as well but of course the report, code, and presentation must be completely developed by the group members themselves. More details on this work will be forthcoming.
• Late homework submissions will be accepted up to 48 hours beyond the deadline, for a 20% grade deduction. No exceptions unless a true emergency arises (proper documentation is required in such cases).
• Handing in your homeworks: All homework, both written and code, must be submitted through via MyCourses. Note that for all programming homeworks/labs, they must be (easily) executable on the CS lab Linux machines (i.e. please no Visual Studio projects, etc). Programming must be done primarily in Python (but R/MatLab are permitted for statistical analysis/visualization purposes).
• Homework grades can be disputed within one week after the graded work is handed back. Dispute the grade with the instructor, not the grader. Your grades will be posted on MyCourses.
• Hopefully there is no need to link to the departmental policy on academic honesty, but it will be enforced if necessary.

Required Materials

• Nature-Inspired Optimization Algorithms (NIOA), 1st Edition, Xin-She Yang, Elsevier, 2014
• Artificial Intelligence: A Modern Approach, 3rd edition, Russell & Norvig, Prentice Hall, 2009 (Selected chapters)
• Selected research papers

Additional Resources

• The Matrix Cookbook, a very handy reference you will want to have on hand.
• The Course Schedule, including information about reading and homework assignments, etc., will be linked from the course web page. I will also make any slides used available here after the relevant session.

Grading

• Rescheduling an Exam

  Quizzes can not be made up except for real emergencies in which case proper documentation (like a doctor's note) will be required. If at all possible, you should contact me prior to the exam. Oversleeping, cars that don't start etc. do not constitute a valid excuse. No exceptions!
  
  RIT's Academic Senate revised the Final Examination Policies on March 28, 2013. Please refer to the policies for related questions.

• Course Withdrawal

  During the add/drop period, you may drop this course and it will disappear from your transcript. After that time, you can only withdraw from the course; the course will appear on your transcript with a grade of W. See the institute's calendar regarding the add/drop period and latest withdrawal date.

• Disability Services

  RIT is committed to providing reasonable accommodations to students with disabilities. If you would like to request accommodations such as special seating or testing modifications due to a disability, please contact the Disability Services Office. It is located in the Student Alumni Union, Room 1150; the web site is www.rit.edu/dso. After you receive accommodation approval, it is imperative that you see me during office hours so that we can work out whatever arrangement is necessary.

• Academic Integrity

  The DCS Policy on Academic Honesty will be enforced.
  You should only submit work that is completely your own. Failure to do so counts as academic dishonesty and so does being the source of such work. Submitting work that is in large part not completely your own work is a flagrant violation of basic ethical behavior and will be punished according to department policy.

• Policy on Large Language Models

  The policy on using large language models (LLMs), part of a broader class of statistical learning models labeled as "generative AI", for this course is simple -- please read the above strict policy "Academic Integrity" for this class. Using an LLM to write your code/text will be treated as not producing your own work (such as copying one of your classmates' work) and will be handled accordingly -- you must produce work that is completely your own. Adhering to this policy is further for your personal benefit -- you get what you put into this class, and to master the craft of machine learning, you must work through the mathematics and do the thinking for yourself in order to truly develop the machine learning literacy this class aims to provide.