Scientific Lectures //
Recent Advanced in Deep Learning: Learning Structured, Robust, and Multimodal Models
Ruslan Salakhutdinov, Ph.D. - Assistant Professor- Department of Computer Science and Statistical Sciences, University of Toronto
Presented: March 11, 2014
ABSTRACT: Building intelligent systems that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many Artificial Intelligence tasks, including visual object recognition, information retrieval, speech perception, and language understanding.In this talk I will first introduce a broad class of hierarchical probabilistic models called Deep Boltzmann Machines (DBMs) and show that DBMs can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will then describe a new class of more complex models that combine Deep Boltzmann Machines with structured hierarchical Bayesian models and show how these models can learn a deep hierarchical structure for sharing knowledge across hundreds of visual categories, which allows accurate learning of novel visual concepts from few examples. Finally, I will introduce deep models that are capable of extracting a unified representation that fuses together multiple data modalities. I will show that on several tasks, including modelling images and text, video and sound, these models significantly improve upon many of the existing techniques.
Information shared in this lecture was requested be held from public access. MRN employees can access the presentation here.