CBMM Brains, Minds, and Machines Seminar Series: Compositional Generative Networks & Adversarial Examiners: Beyond the Limitations of Current AI
Description
Please note the change in start time, this talk will start at 2:30 PM (ET) on May 4, 2021.
Abstract: Current AI visual algorithms are very limited compared to the robustness and flexibility of the human visual system. These limitations, however, are often obscured by the standard performance measures (SPMs) used to evaluate vision algorithms which favor data-driven methods. SPMs, however, are problematic due to the combinatorial complexity of natural images and lead to unrealistic expectations about the effectiveness of current algorithms. We argue that tougher performance measures, such as out-of-distribution testing and adversarial examiners, are required to realistically evaluate vision algorithms and hence to encourage AI vision systems which can achieve human level performance. We illustrate this by studying object classification where the algorithms are trained on standard datasets which have limited occlusion but are tested on datasets where the objects are severally occluded (out-of-distribution testing) and/or where adversarial patches are placed in the images (adversarial examiners). We show that standard Deep Nets perform badly under these types of tests but Generative Compositional Nets, which perform approximate analysis by synthesis, are much more robust.
---
This talk will be hosted remotely via Zoom.
Zoom link: https://mit.zoom.us/j/95505708173?pwd=cjBLVlZWYXNXcDBIanRKMWZNNXZuZz09
Passcode: 522130
Speaker Bio
Professor Alan L. Yuille is a Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University. He directs the research group on Compositional Cognition, Vision, and Learning. He is affiliated with the Center for Brains, Minds and Machines, and the NSF Expedition in Computing, Visual Cortex On Silicon.
Alan Yuille received a BA degree in mathematics from the University of Cambridge in 1976. His Ph.D. on theoretical physics, supervised by Prof. S.W. Hawking, was approved in 1981. He was a research scientist in the Artificial Intelligence Laboratory at MIT and the Division of Applied Sciences at Harvard University from 1982 to 1988. He served as an assistant and associate professor at Harvard until 1996. He was a senior research scientist at the Smith-Kettlewell Eye Research Institute from 1996 to 2002. He was a full professor of Statistics at the University of California, Los Angeles, as a full professor with joint appointments in computer science, psychiatry, and psychology. He moved to Johns Hopkins University in January 2016. His research interests include computational models of vision, mathematical models of cognition, medical image analysis, and artificial intelligence and neural networks.