- This event has passed.
“Explaining visual understanding: Learn to reason about the perceived world” – Talk by Prof. Gal Chechik
March 3, 2020 @ 2:00 pm - 3:00 pm IST
Part of The Israel Statistical Association workshop: Explainable AI (XAI) workshop
Title: Explaining visual understanding: Learn to reason about the perceived world.
Speaker: Prof. Gal Chechik
AI aims to build systems that can interact with their environment, with people and with other agents in the real world. This vision poses hard algorithmic challenges for learning. Such systems are often required to learn to generalize effectively from few samples, to communicate their understanding in ways that are natural to people, and “use common sense” to take into account the unseen context of an image. I will discuss several research thrusts for facing these challenges. First, an unsupervised model of the expectations of a human listener that yields informative communication about images. Second, a cooperative learning algorithm to teach networks to communicate about images using natural language. Finally, I will discuss leveraging compositional structures in attribute space to learn from descriptions without any visual samples.
The work is a summary of a series of papers, done in collaboration with
Y. Atzmon, S. Bengio, L. Bracha, J. Berant, A. Globerson, R. Hertzig, K. Murphi, D. Parikh, M. Raboh, R. Vednatam, G. Vered,
Gal Chechik is an Assoc. Prof at the Gonda Brain Institute at Bar-Ilan University and a director of AI research at NVIDIA. His current research spans learning in brains and machines, including large-scale learning algorithms for machine perception, and analysis of changes of mammalian brains. In 2018, Gal joined NVIDIA as the founder and head of nvidia’s research in Israel. Prior to that, Gal was a staff research scientist at Google Brain and Google research developing large-scale algorithms for machine perception, used by millions daily. Gal earned his PhD in 2004 from the Hebrew University, and completed his postdoctoral training at Stanford CS department. In 2009, he started the learning systems lab at the Gonda center of Bar Ilan university, and was appointed an associate professor in 2013 Gal authored ~85 refereed publications, ~35 patents, including publications in Nature Biotechnology, Cell and PNAS.