Skip Course Information

Course Information

Instructor Info:Jaime Davila
Office Extension x5687
Term: 2013F
Meeting Info: Tuesday Thursday
10:30 AM - 11:50 AM Adele Simmons Hall (ASH) 111
10:30 AM - 11:50 AM Adele Simmons Hall (ASH) 111
Description:

This course will expose students to two important subfields of the artificial intelligence literature, as well as to their intersection: artificial neural networks and evolutionary computation. Students will both learn basic theory and state-of-the-art  work in these fields by reading and commenting on primary sources of current research. Students will also have the opportunity to work with software packages implementing these two machine learning techniques and implementing their own projects/experiments. Particular attention will be placed on using these techniques in human-cognition-like tasks.

By the end of this course successful students will be knowledgable on the basic theory related to artificial neural networks and evolutionary computation. Successful students will also know how find, understand, and apply both these techniques and recent research in these areas to their own hands-on interests.

Students will be evaluated based on two primary types of output:

  • a number of short review papers and/or presentations they will produce throughout the semester about the theory and current practice of artificial neural networks and evolutionary computation.
  • a longer paper and presentation on the application of artificial neural networks and evolutionary computation to a particular problem of their choosing. This longer piece of work, which will be due at the end of the semester, will involve submitting shorter preparatory pieces throughout earlier parts of the semester.
Course Objectives:

By the end of this course successful students will be knowledgable on the basic theory related to artificial neural networks and evolutionary computation. Successful students will also know how find, understand, and apply both these techniques and recent research in these areas to their own hands-on interests.

Evaluation Criteria:

Students will be evaluated based on two primary types of output:

  • a number of short review papers and/or presentations they will produce throughout the semester about the theory and current practice of artificial neural networks and evolutionary computation.
  • a longer paper and presentation on the application of artificial neural networks and evolutionary computation to a particular problem of their choosing. This longer piece of work, which will be due at the end of the semester, will involve submitting shorter preparatory pieces throughout earlier parts of the semester.
Additional Info:

Outside of class meeting times, students can expect having to work between five and ten hours a week for this course.

This course will require no textbook. Our main sources of information will be publicly available documentation on artificial neural networks and genetic algorithms, as well as papers from prominent conferences and publications in the field.

Course policy on incompletes: students will be elegible to receive an incomplete at the end of the semester only if they have a serious, valid health or personal reason that keeps them from completing work in a timely mannery. Students are strongly adviced to notify the course instructor as soon as such a circumstance arrises. Even in those cases, it is the instructor's prerogative to grant an incomplete or not.

Regarding plagiarisim and academic dishonesty: All Hampshire College students and faculty, whether at Hampshire or at other institutions, are bound by the ethics of academic integrity. The entire description and college policy can be found in Non Satis Non Scire at handbook.hampshire.edu under Academic Policies/Ethics of Scholarship. Plagiarism is the representation of someone else’s work as one’s own. Both deliberate and inadvertent misrepresentations of another’s work as your own are considered plagiarism and are serious breaches of academic honesty and integrity. All sources used or consulted in the process of writing papers, examinations, preparing oral presentations, course assignments, artistic productions, and so on, must be cited. Sources include material from books, journals or any other printed source, the work of other students, faculty, or staff, information from the Internet, software programs and other electronic material, designs and ideas.

All cases of suspected plagiarism or academic dishonesty will be referred to the Dean of Advising who will review documentation and meet with student and faculty member. Individual faculty, in consultation with the Dean of Advising, will decide the most appropriate consequence in the context of the class. This can range from revising and resubmitting an assignment to failing the course. Beyond the consequence in the course, CASA considers first offenses as opportunities for education and official warning. Multiple or egregious offenses will have more serious consequences. Suspected instances of other breaches of the ethics of academic integrity, such as the falsification of data, will be treated with the same seriousness as plagiarism and will follow the same process.