Recent Advances in Deep Learning (remote)
In this talk I will first introduce a broad class of deep learning models and show that they can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will introduce models that can find semantically meaningful representations of words, learn to read documents and answer questions about their content. Specifically, I will focus on recurrent neural network models that integrate multi-hop architectures with novel attention mechanism, along with its extensions that make use of external linguistic knowledge. I will further introduce the notion of “Memory” as being a crucial part of an intelligent agent’s ability to plan and reason in partially observable environments and demonstrate a deep reinforcement learning agent that can learn to store arbitrary information about the environment over long time lags. I will show that on several tasks these models significantly improve upon many of the existing techniques.