Embodied Question Answering is a new AI task where an agent is spawned at a random location in a 3D environment and asked a question ("What color is the car?"). In order to answer, the agent must first intelligently navigate to explore the environment, gather information through first-person (egocentric) vision, and then answer the question ("orange").
This post summarizes the latest joint research between researchers at Georgia Tech and Facebook on using visualization to make sense of deep learning models, published at IEEE VIS’17, a top visualization conference. While powerful deep learning models have significantly improved prediction accuracy, understanding these models remains a big challenge. Deep learning models are more difficult … Continue reading Visualizing Deep Learning Models at Facebook
Please join us on Thursday 2/22/2018 for the ML@GT Center Spring Event featuring talks from internal faculty and invited speakers. Event runs from 10AM to 5PM in the Klaus Atrium. Invited Speakers Sanjeev Arora - Princeton University Sanjeev Arora is Charles C. Fitzmorris Professor of Computer Science at Princeton University. He is interested in … Continue reading ML@GT Spring Event – 2/22
Advances in deep learning of representation have resulted in powerful generative approaches on modeling continuous data like time series and images, but it is still challenging to correctly deal with discrete structured data, such as chemical molecules and computer programs. To tackle these challenges, there has been many improvements in formalization of structure generation that … Continue reading Syntax-Directed Variational Autoencoder for Structured Data
The list of accepted papers at ICLR 2018 was released last week and Machine Learning at Georgia Tech (ML@GT) had a strong presence. Out of 935 submissions, 23 oral and 314 conference papers were accepted (roughly 36%). We are pleased to announce that Georgia Tech had 10 conference papers this year, with 1 of them … Continue reading ICLR 2018 accepted papers and ML@GT