[Monday, October 22, 2018 at 8:30 AM in Wegmans Hall 2506]
Machine Learning, as a branch of Artificial Intelligence, is now starting to contribute towards every aspects of human life. It provides a powerful set of mathematical tools to facilitate the scientific explorations over a large volume of data. In combination with the recent development of powerful machine learning techniques and the abundance of audio-visual data of human life, it is now becoming possible to detect human behaviors using a complete data-centric approach. In this thesis we explore this possibility through a number of experiments in the context of public speaking.
This exploration has been conducted from several directions. First, we use the machine learning models to analyze the body language of the speakers. We capture the repetitive body movement patterns using an unsupervised technique. We design an interface namedAutoMannerthat uses these patterns to help the public speakers become aware of their idiosyncratic body movements. Second, we analyze the effects of narrative trajectories or the styles of story telling on the viewers of public speaking. Third, we predicted the TED talk ratings using a classical machine learning approach and a deep neural network based approach. We show that the neural network based approach can predict human behaviors with better accuracy than the classical machine learning approach. Additionally, the neural networks require comparatively lesser application-domain-specific knowledge. Consequently, the neural network approach could be utilized not only in the public speaking domain, but also in a wider range of other application areas. Finally, we design a real-time intervention technique to provide live information to the speakers while minimizing distraction.
Reception with light refreshments to follow at 10:30am in Wegmans Hall 2506
Advisor: Professor M. Ehsan Hoque (CS)
Committee: Professor Mark Bocko (ECE), Professor Gonzalo Mateos (ECE), Professor Daniel Gildea (CS)
October 22, 2018, 12:00 PM
Professor Kobbi Nissim: A Computer Scientist and A Legal Scholar Walk Into a Bar
[Monday, October 22, 2018 at 12:00 PM in Wegmans Hall 1400] We will explore some of the gaps between technical and legal conceptions of privacy and argue for the development of rigorous paradigms for bridging between or even unifying these concepts. We will present strategies and first results towards doing so considering an example from the GDPR and differential privacy.
October 26, 2018, 01:00 PM
Raymond Ptucha: TBD
[Friday, October 26, 2018 at 1:00 PM in Wegmans Hall 2506] TBD
[Monday, October 29, 2018 at 12:00 PM in Wegmans Hall 1400] Intelligent systems are poised to become ubiquitous, but there is a snag: artificial intelligence is far from being able to understand (e.g., via natural language or vision) and reason about the world in general. Machine learning (ML) has had significant success for specific classes of problems, but generating the massive, tailored training data sets that are needed to make ML algorithms work reliably is hard, and transferring that knowledge to new domains remains even more challenging. Crowdsourcing has provided a means of collecting data at scale, but has historically been an offline process that takes days or weeks to produce final outcomes. In this talk, I will discuss my lab's work on real-time and "instantaneous" crowdsourcing and show how human insight can be brought to bear on novel problems when and where they are encountered by intelligent systems in the wild. The resulting "hybrid intelligence" systems can learn, on-the-fly, to perform tasks more reliably and more robustly than either humans or machines could alone.
November 30, 2018, 01:00 PM
Guoyu Lu: TBD
[Friday, November 30, 2018 at 1:00 PM in Wegmans Hall 2506] TBD