Skip to content
Texas A&M University
Mathematics

Public lectures

Fall 2020

 

Date:October 16, 2020
Time:5:00pm
Location:Zoom
Speaker:Richard Baraniuk, Rice University
Title:Going Off the Deep End with Deep Learning.
Abstract:Video at: https://www.math.tamu.edu/conferences/SIAMTXLA/plenary.html A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation. For instance, visual object recognition involves the unknown object position, orientation, and scale, while speech recognition involves the unknown voice pronunciation, pitch, and speed. Recently, a new breed of deep learning algorithms have emerged for high-nuisance inference tasks that routinely yield pattern recognition systems with super-human capabilities. Similar results in language translation, robotics, and games like Chess and Go plus billions of dollars in venture capital have fueled a deep learning bubble and public perception that actual progress is being made towards general artificial intelligence. But fundamental questions remain, such as: Why do deep learning methods work? When do they work? And how can they be fixed when they don't work? Intuitions abound, but a coherent framework for understanding, analyzing, and synthesizing deep learning architectures remains elusive. This talk will discuss the important implications of this lack of understanding for consumers, practitioners, and researchers of machine learning. We will also briefly overview recent progress on answering the above questions based on probabilistic graphs and splines.

Date:October 24, 2020
Time:3:00pm
Location:Zoom
Speaker:P. Kuchment, TAMU
Title:Our Mathematical Universe
Abstract:Video: https://www.math.tamu.edu/outreach/highschoolcontest/2020_Public_Lecture.mp4 Abstract: Everyone has heard many times that "mathematics is useful in sciences, engineering, etc." It is, indeed. However, no one has been able (at least in the speaker's opinion) to answer the question "WHY does this happen?" Mathematicians are not big fans of discussing this topic (physicists are). The speaker is really going out on a limb (please, do not kill the messenger) presenting a discussion of (not an answer to) this question, with examples of various major historical developments in and applications of mathematics. No background in mathematics is needed (or is enough).