Dr. Stuart Geman, James Manning Professor of Applied Mathematics at Brown University, will be speaking at JHU's Center for Imaging Science's 15th anniversary celebration. His presentation will take place on the second day of the event, May 18th at 9:30 am on the JHU Homewood Campus in Hodson Hall. His presentation should be particularly interesting for those affiliated with the Science of Learning Institute.
Description: Google engineers routinely train query classifiers, for ranking advertisements or search results, on more words than any human being sees or hears in a lifetime. A human being who sees a meaningfully new image every second for one-hundred years will not see as many images as Google has in its libraries for training object detectors and image classifiers. Children learn more efficiently, achieving nearly perfect competence on about 30,000 categories in their first eight years. Upper bounds on the number of training samples needed to learn a classifier with similar competence can be derived using the Vapnik-Chervonenkis dimension, or the metric entropy, but these suggest that not only does Google need more examples, but all of evolution might fall short.
This talk will discuss machine learning and human learning, with a focus on representation. It will be argued that brains simulate rather than classify, suggesting that the rich relational information available in an imagined world argues against abstraction and in favor of topological, almost literal, representation. Speculation concerning physiological mechanisms that would support topologically organized neuronal activity patterns will be discussed.
To see the entire event brochure of the Center for Imaging Science's 15th Anniversary Celebration, click here.