Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead

Hugo Larochelle, a researcher at Google Brain, recently visited Georgia Tech's campus as a part of the Machine Learning Center's Fall Seminar Series. Larochelle drew an enormous crowd with students and faculty filling up the room, leaving many audience members standing or sitting on any patch of carpet they could find. During his talk, "Few-shot … Continue reading Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead

The Natural Language Decathlon: Multitask Learning as Question Answering

In August 2018, Bryan McCann of Salesforce made the trip from Palo Alto, Calif. to Atlanta, Ga. as a part of the Machine Learning Center at Georgia Tech’s Seminar Series. Students and faculty packed the room to hear McCann present his talk, "The Natural Language Decathlon: Multitask Learning as Question Answering". Abstract Deep learning has improved … Continue reading The Natural Language Decathlon: Multitask Learning as Question Answering

Reaching Beyond Human Accuracy With AI Datacenters

Gregory Diamos of Baidu’s Silicon Valley AI Lab (SVAIL), recently made the trip from Silicon Valley to Atlanta as a part of the Machine Learning Center at Georgia Tech's Seminar Series. Diamos presented his talk, "Reaching Beyond Human Accuracy With AI Datacenters" to a room packed with Georgia Tech students of all levels, faculty members … Continue reading Reaching Beyond Human Accuracy With AI Datacenters

What Makes a New Word Stick?

By Ian Stewart The language that people use to communicate online is in constant flux. People may have once written "haha" to indicate laughter but over time have adopted "lol" instead. Entire dictionaries and websites such as UrbanDictionary.com are dedicated to tracking the ebb and flow of the latest slang (i.e. nonstandard) words that propagate … Continue reading What Makes a New Word Stick?

Learning Rigidity and Scene Flow Estimation

By Zhaoyang Lv We live in a three-dimensional (3D), dynamic world every day. Being able to perceive 3D high-resolution motion is a fundamental ability of our perception system, which enables us to perform versatile jobs. At the age when we are building intelligent robots, autonomous vehicles, and augmented reality toolkits, how can we also enable … Continue reading Learning Rigidity and Scene Flow Estimation