MSE 2400
001
Evolution and Learning in
Computational & Robotic Agents
Spring 2016

SYLLABUS


Meetings
Lecture TR  2:30-3:45 (Mendel G86)
Lab       W  1:30-4:20 (Mendel G92)
Instructor Dr. Tom Way
160A Mendel Science Center
Email:   thomas.way@villanova.edu
Skype:  DrTomWay
Office Hours M 10:00-12:00
T  1:00-2:30
R  3:45-5:00
Other times via email, Skype or appointment
Teaching Assistant Hema Chandra <hethapu@villanova.edu>

Programming Assistants' schedule
CSC Peer Tutoring

Textbook We will rely primarily on online resources and handouts.
Web Site
http://www.csc.villanova.edu/~tway and follow the link for MSE 2400
Catalog Course
Description

Science of computers and robots that learn and evolve in ways that mimic biological systems. This course explores how software designers and artificial intelligence researchers draw inspiration from biology and learning theory to design and experiment with computer systems and robots that learn from sometimes massive amounts of data and adapt to changes in their environment. It is increasingly important to understand the capabilities and impact on individuals and society of computer and robotic systems that can appear to learn and evolve. Laboratory experimentation involves applying the scientific method and data intensive analysis by using software tools, developing computer code, and controlling robots. No prior programming experience is required. This course fulfills one semester of the Natural Science requirement of the Core Curriculum in the College of Liberal Arts and Sciences.

Learning Objectives & Outcomes After taking this course, including lecture and lab components, the student will be able to:
  1. Explain the basic steps behind a variety of computational, or machine, learning and evolution technologies, such as neural networks, Bayesian learning, automated theorem proving, decision tree induction, logical-concept learning, and genetic algorithms.
  2. Discuss the strengths and limitations of these techniques.
  3. Identify and discuss practical examples of machine learning techniques in modern life.
  4. Read and be able to discuss seminal technical papers to recognize the roots of developments in machine learning in general and the specific subtopics covered in the course.
  5. Describe the main components of robotic systems.
  6. Discuss ethical issues behind the use of these techniques.
  7. Conduct a presentation on a Machine Learning topic of your choosing based on your research in the topic.
  8. Write, revise and run computer programs written in the Python programming language, and use numerous specialized software tools to explore the topics of the course.
Course Organization The course meetings will typically consist of lecture and discussion on "lecture" meeting days and hands-on experimental laboratory assignments on "lab" meeting days. However, because our laboratory is entirely contained within each of our computers, it is possible that lab work will be done during some lecture meeting time and vice versa.

All course materials, including lecture slides, lab assignments, assigned readings, internet-based resources and software, will be gathered on our course website. In particular, on the Schedule page of the course website, you will find links to most of these materials, while more general resources and materials will be found on the Resources page.

Note that, while the plan for this course has been structured as outlined here and in the Schedule, it should also be considered flexible within constraints of covering the necessary topics. In other words, as with any honest scientific endeavor, as we make discoveries our plans and directions may change.

Grading policy
Grading will be based cumulative learning activities, homework and lab assignments, participation, contribution to class, exams, and ultimately your personal productivity as it relates to the work of the semester. Participation and attendance in particular will be vital!

10%  Homework assignments
40%  Lab assignments and projects
15%  Midterm exam
25%  Final exam
10%  Participation (attendance, class discussion, intellectual contribution to class)

Final grades
94 A 87 B+ 77 C+ 67 D+
90 A- 84 B 74 C 64 D
80 B- 70 C- 60 D-
Makeup Policy
No missed or late assignments, exams or laboratory assignments without prior excuse. Each case will be handled separately based on its own merits. Each student is responsible for what is covered and assigned in any classes which they miss. Abuse of this policy will result in a loss of leniency.
Late Assignment Policy
No assignments will be accepted late without the direct consent of the instructor prior to the due date of the assignment.  Typical penalty is 10% off for each day an assignment is late. Absolutely no assignments will be accepted beyond the date of the final exam.
Academic Integrity All students are expected to uphold Villanova’s Academic Integrity Policy and Code. Any incident of academic dishonesty will be reported to the Dean of the College of Liberal Arts and Sciences for disciplinary action. For the College’s statement on Academic Integrity, you should consult the Enchiridion. You may view the university’s Academic Integrity Policy and Code, as well as other useful information related to writing papers, at the Academic Integrity Gateway web site: http://library.villanova.edu/Help/AcademicIntegrity

Please be cognizant of the difference between individual and group projects, and use good judgment in following the University's policy on Academic Integrity. Severe academic penalities will be imposed for violations of this policy, such as receiving at a minimum 0% credit for an assignment, or at the maximum a failing grade for the course, at the discretion of the instructor.

Accommodations Office of Disabilities and Learning Support Services:
Students with disabilities who require reasonable academic accommodations should schedule an appointment to discuss specifics with me. It is the policy of Villanova to make reasonable academic accommodations for qualified individuals with disabilities. You must present verification and register with the Learning Support Office by contacting 610-519-5176 or at learning.support.services@villanova.edu or for physical access or temporary disabling conditions, please contact the Office of Disability Services at 610-519-4095 or email Stephen.mcwilliams@villanova.edu. Registration is needed in order to receive accommodations.

It is always recommended to seek out extra assistance and advice early rather than waiting, and friendly and qualified help is there for you.

Last updated: 04/03/2017