|
|
Robotics Institute
Seminar, March 25
Time
and Place | Seminar Abstract | Speaker
Biography | Speaker Appointments
Learning in Artificial Sensorimotor Systems
Dr. Daniel D. Lee
Assistant Professor
Dept. of
Electrical and Systems Engineering, University of Pennsylvania
|
Time and Place |
Mauldin
Auditorium (NSH 1305)
Refreshments
Talk
Many algorithms
in machine learning involve changing the underlying dimensionality of the data
set. Unsupervised learning techniques
such as principal components analysis typically involve dimensionality
reduction, whereas supervised learning techniques such as support vector
machines can be understood as mapping the data to a higher dimensional
space. Equivalent problems emerge when
considering information processing in sensorimotor systems. Sensory processing requires mapping
high-dimensional sensory inputs onto a smaller number of perceptually-relevant
features, whereas motor learning involves driving a large number of actuator
parameters with a smaller number of control variables. I will describe some of our recently
developed learning algorithms that utilize changes in dimensionality, and
demonstrate their application on some prototypical robotic systems.
|
Speaker Biography |
Daniel D. Lee is currently an Assistant Professor of
Electrical and Systems Engineering at the
For appointments, please contact Marliese Bonk
(marliese+@andrew.cmu.edu).
|
Related Material |
- Slides of the presentation
The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.