Tao Wins Best Paper Award at Artificial Intelligence and Statistics Conference

A mathematician by trade, Molei Tao, typically uses mathematics to design algorithms and solve physical science problems like how planets move. Recently, he became attracted to machine learning, an area that according to him, contains numerous interesting problems that are mathematically exciting and can benefit from modern mathematical tools. This year, Tao published his first… Continue reading Tao Wins Best Paper Award at Artificial Intelligence and Statistics Conference

ML@GT Makes a Strong Showing at Premier European Computer Vision Conference

This year’s European Conference on Computer Vision (ECCV) showcases 1,360 papers – 15 of them from the Machine Learning Center at Georgia Tech (ML@GT.) The papers cover a vast array of topics including an idea on how to improve vision and language navigation and a new model that is learning to generate grounded visual captions… Continue reading ML@GT Makes a Strong Showing at Premier European Computer Vision Conference

New Algorithm Follows Human Intuition to Make Visual Captioning More Grounded

Annotating and labeling datasets for machine learning problems is an expensive and time-consuming process for computer vision and natural language scientists. However, a new deep learning approach is being used to decode, localize, and reconstruct image and video captions in seconds, making the machine-generated captions more reliable and trustworthy. To solve this problem, researchers at… Continue reading New Algorithm Follows Human Intuition to Make Visual Captioning More Grounded

ML@GT to Present Nine Papers at Competitive Machine Learning Conference

The International Conference on Machine Learning (ICML) received nearly 5,000 submissions for its 2020 conference and accepted 1,088 papers. Machine Learning Center at Georgia Tech (ML@GT) researchers authored nine accepted papers. The papers explore topics like privacy, semantics in predictive agents, data science, and artificial intelligence. One paper, Boosting Frank-Wolfe by Chasing Gradients, proposes a new state-of-the-art algorithm for constrained… Continue reading ML@GT to Present Nine Papers at Competitive Machine Learning Conference

ML@GT to Present Diverse Research Interests at CVPR 2020

For computer vision fans, the Computer Vision and Pattern Recognition (CVPR) conference is a significant annual event, regularly drawing thousands of attendees and paper submissions. The  Georgia Institute of Technology had nine papers by 33 authors accepted in the conference, taking place online this year starting June 14. Accepted papers covered a wide range of… Continue reading ML@GT to Present Diverse Research Interests at CVPR 2020

Georgia Tech Researchers Presenting Work Virtually at Top AI Conference Due to COVID-19

Due to the rapid spread of coronavirus (COVID-19) and resulting travel restrictions, Georgia Tech students and faculty will now be presenting their research virtually at the International Conference on Learning Representations (ICLR), one of the biggest artificial intelligence (AI) conferences in the world, April 25 through 30. With 17 papers to present, researchers will create a… Continue reading Georgia Tech Researchers Presenting Work Virtually at Top AI Conference Due to COVID-19

Working Towards Explainable and Data-efficient Machine Learning Models via Symbolic Reasoning

By Yuan Yang In recent years, we have experienced the success of modern machine learning (ML) models. Many of them have led to unprecedented breakthroughs in a wide range of applications, such as AlphaGo beating a world champion human player or the introduction of autonomous vehicles. There has been a continuous effort, both from industry… Continue reading Working Towards Explainable and Data-efficient Machine Learning Models via Symbolic Reasoning

Escaping Saddle Points Faster with Stochastic Momentum

By Jun-Kun Wang, Chi-Heng Lin, and Jacob Abernethy SGD with stochastic momentum (see Figure 1 below) has been the de facto training algorithm in nonconvex optimization and deep learning. It has been widely adopted for training neural nets in various applications. Modern techniques in computer vision (e.g.[1,2]), speech recognition (e.g. [3]), natural language processing (e.g.… Continue reading Escaping Saddle Points Faster with Stochastic Momentum

Learning to Cooperate in Multi-Agent Environments

By Jiachen Yang Over the years, human intelligence has evolved to work within a shared environment with other humans to do more than play Atari games or solve Rubik’s cubes alone in our rooms. The presence of other people demands our ability to handle a wide spectrum of complex interactions — we cooperate with colleagues… Continue reading Learning to Cooperate in Multi-Agent Environments

Snapshots from NeurIPS2019

What once started as a small conference with a few hundred people interested in neural information processing systems has over the years turned into one of the largest artificial intelligence conferences in the world. This year, over 13,000 people attended the 33rd conference on Neural Information Processing Systems (NeurIPS) in Vancouver, British Columbia. Over the… Continue reading Snapshots from NeurIPS2019