For our next “Control meets Learning” virtual seminar, we are excited to have Prof. Patricio Vela from Georgia Tech. The talk will start at 9:00 AM Pacific Time on Wednesday, April 28, 2021. To join the seminar, you may use the Zoom link below or watch the livestream on YouTube.
Zoom:
https://caltech.zoom.us/j/84222304300YouTube:
https://youtu.be/4EesPjQq0JUTitle: On the Structure of Learning: What’s in the Black Box?
Abstract: Deep learning algorithms preceded the theory, thus there is sometimes the viewpoint that deep learning is not well understood. This viewpoint is further reinforced by current work seeking to understand the optimization landscape of the training process and why it works, as well as to understand why certain negative outcomes occur in the deployment or testing phase. However, if one ignores the how of the learning process and focuses on the what of the learning process, deep networks are less mysterious and conform to what is known about best practice for signal/function approximation and estimation. Given this understanding, it is then possible to contemplate comparably designed “shallow” networks with equivalent or more favorable properties for low to moderately dimensional input/output regression problems. The shallow networks work well for feedback control systems and exhibit single- or few-shot learning. For higher dimensional and image-like inputs, deep networks assist with feature space generation, but the decisions made still rely on shallow learning theory. In these cases, deep learning is better understood as a process for learning the composition of a feature mapping and a decision/regression function. The output representation chosen for the second step influences the learning process and can have a demonstrable impact on the performance of the learnt solution. Strong performance is therefore just as dependent on structural choices made about the network’s architecture and loss functions (the what) as the underlying learning algorithms and how they work. Understanding these properties is important for learning deployed in the closed-loop.
Bio: Patricio A. Vela is an associate professor in the School of Electrical and Computer Engineering at the Georgia Institute of Technology. Dr. Vela's research focuses on geometric perspectives to control theory and computer vision, particularly how concepts from control and dynamical systems theory can serve to improve computer vision algorithms used in the decision-loop. More recent efforts expanding his research program involve studying the role of machine learning in adaptive control and autonomous robotics, and investigating how modern advances in adaptive and optimal control theory may improve locomotion effectiveness for biologically-inspired robotics. These efforts support a broad program to understand important research challenges associated with autonomous robotic operation in uncertain environments. Dr. Vela received a B.S. and a Ph.D. from the California Institute of Technology.
--
FROM 211.161.243.*