Semester.ly

Johns Hopkins University | EN.580.691

Learning, Estimation and Control

3.0

credits

Average Course Rating

(4.53)

This course introduces the probabilistic foundations of learning theory. We will discuss topics in regression, estimation, Kalman filters, Bayesian learning, classification, reinforcement learning, and active learning. Our focus is on iterative rather than batch methods for parameter estimation. Our aim is to use the mathematical results to model learning processes in the biological system. Recommended Course Background: Probability and Linear Algebra.

Spring 2013

(4.33)

Spring 2014

(4.8)

Spring 2023

(4.47)

Spring 2013

Professor: Reza Shadmehr

(4.33)

The best aspects of the course included the interesting material that was well covered in lectures and the assignments that helped to reinforce the material. The worst aspects of the course included the hefty and sometimes unclear homework assignments. Students also felt that some of the mathematical concepts used to teach the course were weak. The course would improve if some of the mathematical concepts were reviewed before incorporating them into the lessons so that students could understand how they are integrated into learning theory. Prospective students should be comfortable with linear

Spring 2014

Professor: Learning Theory

(4.8)

The highlights of this course were the variety of guest speakers and the knowledge base of the instructor. Additionally, there was a dinner at Hopkins Club, and guest speakers were available for questions after the lectures. Many students thought the late time of the class and the term paper were the worst aspects of the course. Suggestions for improvement included holding class at an earlier time, and basing the grade on smal er assignments. Prospective students should know this course is interesting and enjoyable, and gives many opportunities for networking.

Spring 2023

Professor: Reza Shadmehr

(4.47)