Blogs

Title: Visipedia - A system composed of data, machines and people for organizing visual knowledge Speaker:  Pietro Perona Abstract: Visipedia is a network of people and machines designed to harvest and organize visual information and make it accessible to anyone anywhere. I will explore technical challenges arising from Visipedia and discuss their implications for computer vision,…

Title: Towards Safe Reinforcement Learning Speaker:  Andreas Krause Abstract: Reinforcement learning has seen stunning empirical breakthroughs. At its heart is the challenge of trading exploration -- collecting data for learning better models -- and exploitation -- using the estimate to make decisions. In many applications, however, exploration is a potentially dangerous proposition, as it requires experimenting…

Title: Deep Architectures for Visual Reasoning, Multimodal Learning, and Decision-Making Speaker:  Honglak Lee Abstract: Over the recent years, deep learning has emerged as a powerful method for learning feature representations from complex input data, and it has been greatly successful in computer vision, speech recognition, and language modeling. While many deep learning algorithms focus on a…

Title: Sum-Product Networks: The Next Generation of Deep Models Speaker:  Pedro Domingos Abstract: The two main types of deep learning are function approximation and probability estimation. Function approximators like convolutional neural networks are robust and allow for real-time inference, but are very inflexible, requiring fixed inputs and outputs and detailed supervision. Probability estimators like deep Boltzmann…

Title: The Challenge of Sequential Modeling Speaker:  Yoshua Bengio Abstract:  Deep learning research has been moving forward at a rapid pace in recent years, with progress on many fronts and several major challenges still ahead of us. One of the difficult questions is that of properly modelling sequences. The main tool is the recurrent neural…

Title: Incentive Auctions and Spectrum Repacking Speaker:  Kevin Leyton-Brown Abstract:  This talk will discuss the FCC’s “incentive auction”, which proposes to give television broadcasters an opportunity to sell their broadcast rights, to repack remaining broadcasters into a smaller block of spectrum, and to resell the freed airwaves to telecom companies. The stakes for this auction…

Title: Representations and Models for Collaboratively Intelligent Robots Speaker:  Subramanian Ramamoorthy Abstract: We are motivated by the problem of building autonomous robots that are able to work collaboratively with other agents, such as human co-workers. One attribute of such an autonomous system is the ability to make predictions about the actions and intentions of other agents…

Title: Generating Natural-Language Video Descriptions using LSTM Recurrent Neural Networks Speaker:  Raymond Mooney Abstract: We present a method for automatically generating English sentences describing short videos using deep neural networks. Specifically, we apply convolutional and Long Short-Term Memory (LSTM) recurrent networks to translate videos to English descriptions using an encoder/decoder framework. A sequence of image frames…

Title: Addressing the Practical Challenges of Group Decision Support in a Data-rich World Speaker:  Craig Boutilier Abstract: In a variety of social, business, political and economic contexts, decision making often involves groups of people or multiple stakeholders. Automated decision support for groups is considerably more difficult than for a single stakeholder since it requires aggregating the…