Explaining Blended Matching Pursuit: A Multi-Purpose AI Algorithm

By Cyrille Combettes This is an informal summary of our recent paper Blended Matching Pursuit with my advisor Sebastian Pokutta. It will be presented at the Conference on Neural Information Processing Systems (NeurIPS) in Vancouver, British Columbia, Dec. 8-14, 2019. In this post, we motivate and explain the main ideas behind the design of our … Continue reading Explaining Blended Matching Pursuit: A Multi-Purpose AI Algorithm

12 Questions with Aleksandra Faust on Finding the Right Career and Being Resilient in AI

The Machine Learning Center at Georgia Tech’s Seminar Series draws leading researchers from across academia and industry each semester to present on current topics in machine learning and artificial intelligence, applications for the technologies, and related insights and experiences. The popular series averages more than 100 attendees for each talk. This fall, five experts give talks across … Continue reading 12 Questions with Aleksandra Faust on Finding the Right Career and Being Resilient in AI

Making Artificial Intelligence Work in a Changing Environment

By Adrian Rivera Cardoso and He Wang Machine learning (ML) is changing our lives. We can instantly translate from one language to another, search entire libraries in a matter of seconds, and even prevent credit card fraud. ML’s success is mostly due to the power of artificial neural networks — a machine learning model inspired … Continue reading Making Artificial Intelligence Work in a Changing Environment

Explaining Nonparametric Regression on Low Dimensional Manifolds using Deep Neural Networks

By Minshuo Chen Background and Motivation Deep learning has made significant breakthroughs in various real-world applications, such as computer vision, natural language processing, healthcare, robotics, etc. In image classification, the winner of the $latex 2017$ ImageNet challenge retained a top-$latex 5$ error rate of $latex 2.25\% $ [1], while the data set consists of about … Continue reading Explaining Nonparametric Regression on Low Dimensional Manifolds using Deep Neural Networks

Artificial Intelligence System Gives Fashion Advice

People turn to many different sources for clothing style advice, from magazines to best friends to Instagram. Soon, though, you may be able to ask your smartphone. A University of Texas at Austin computer science team, in partnership with researchers from Cornell Tech, Georgia Tech and Facebook AI Research, has developed an artificial intelligence system … Continue reading Artificial Intelligence System Gives Fashion Advice

ML@GT Alumni Corner: Jason Lin, Seeking Balance between Research, Application, and Problem Solving on the Go

The Machine Learning Center at Georgia Tech is responsible for training the next generation of machine learning and artificial intelligence pioneers. Jason Lin, a recent master’s in computer science graduate who specialized in machine learning and robotics, is one of many students the center is thrilled to see thriving in today’s workforce. Currently a research … Continue reading ML@GT Alumni Corner: Jason Lin, Seeking Balance between Research, Application, and Problem Solving on the Go

Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

By Ramprasaath R. Selvaraju Many popular and well-performing models for multi-modal, vision and language tasks exhibit poor visual grounding -- failing to appropriately associate words or phrases with the image regions they denote and relying instead on superficial linguistic correlations. For example, answering the question “What color are the bananas?” with yellow regardless of their … Continue reading Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded