Semester.ly

Johns Hopkins University | EN.580.491

Learning, Estimation and Control

3.0

credits

Average Course Rating

(4.65)

The course introduces the probabilistic foundations of learning theory. We will discuss topics in regression, estimation, optimal control, system identification, Bayesian learning, and classification. Our aim is to first derive some of the important mathematical results in learning theory, and then apply the framework to problems in biology, particularly animal learning and control of action. Recommended Course Background: AS.110.201 and AS.110.302

Spring 2013

(4.6)

Spring 2014

(4.67)

Spring 2015

(4.67)

Spring 2013

Professor: Reza Shadmehr

(4.6)

The best aspects of this course included the hands-on engineering experience and the opportunity to apply one’s knowledge of material learned in prerequisite courses. One student felt there was not enough guidance from the instructor. Another student felt that he/she had to figure a lot of things out on his/her own and without the instructor’s feedback or support. Suggestions included eliminating having to go to design lecture and providing students with more guidance throughout the semester. Prospective students are encouraged to get ahead of schedule with their design planning and execution.

Spring 2014

Professor: Reza Shadmehr

(4.67)

This class is highlighted by independent, real world projects, and the chance to design and build a complex project with autonomy. The lack of clear guideposts and expectations for projects were the worst aspects of this course. To improve the course students suggested more one-on-one meetings, more rigorous requirements, and additional interaction between the students in the class. Prospective students should know the class requires personal motivation. The intellectual challenge is similar to design team, with the difference of solo projects.

Spring 2015

Professor: Reza Shadmehr

(4.67)

Students enjoyed the interesting material presented by the passionate, clear, and engaging instructor. Students praised the professor for being able to explain technical details of the material without losing sight of the overarching concepts. The TA was very helpful and the homework assignments better clarified concepts learned in class. Students found the assignments to be chal enging and math-intensive. Suggestions for improvement included providing clearer instructions for assignments and more background information concerning course topics for students. Prospective students should be prepared to allocate enough time to complete assignments and have a strong background in linear algebra.