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
By Upol Ehsan, Ph.D. Student, School of Interactive Computing, Georgia Tech (contributing writer; Joshua Preston, GVU Center) If the power of AI is to be democratized, it needs to be accessible to anyone regardless of their technical abilities. As AI pervades all aspects of our lives, there is a distinct need for human-centered AI design… Continue reading Georgia Tech’s Newest AI System Can Mimic Thinking Out Loud and Explain Its Decision to Non-Experts in Real-time
Georgia Tech's Research Horizons Magazine has done a very nice write-up of the ML@GT center, featuring many of our research projects. Machine learning has been around for decades, but the advent of big data and more powerful computers has increased its impact significantly — moving machine learning beyond pattern recognition and natural language processing into a… Continue reading The Minds of the New Machines | Research Horizons | Georgia Tech’s Research News
Machine learning at Georgia Tech was in the spotlight recently as The Center for Machine Learning at Georgia Tech (ML@GT) hosted its spring seminar on Feb. 22 in the Klaus Advanced Computing Building.Billed as a “day of discussions around machine learning,” more than 200 students and faculty from across campus registered for the daylong event.“AI is… Continue reading Ethics Highlight ‘Day of Machine Learning Discussion’ | College of Computing
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").
ML@GT hosted a special a seminar & a reception to celebrate Devi’ Parikh’s IJCAI's 2017 Computers and Thought Award. She will give a talk about her work and there will be a reception to celebrate her award. Date/Time: 9/5/2017 @ 3-4pm with a reception following to celebrate this award. Location: The Engineered Biosystems Building (EBB),… Continue reading Devi Parikh gives a seminar to celebrate her IJCAI 2017 Computers and Thought Award.
Our own Devi Parikh was featured as one of the "Incredible Women Advancing A.I. Research" by Forbes. Congrats to Devi. Devi Parikh is an Assistant Professor in the School of Interactive Computing at Georgia Tech and a Visiting Researcher at Facebook AI Research (FAIR). After receiving her masters and Ph.D. in Electrical and Computer Engineering… Continue reading Meet These Incredible Women Advancing A.I. Research, including our very own Devi Parikh
We are pleased to announce that one of our newest faculty members, Dhruv Batra, who recently joined the School of Interactive Computing, is the recipient of the ONR Young Investigator Program (YIP) Award. The ONR YIP is a highly competitive and prestigious award for early-career researchers whose scientific pursuits show outstanding promise for supporting the… Continue reading Congrats to Dhruv Batra for being Awarded the ONR YIP 2017
School of Electrical and Computer Engineering Seminar Title. Challenges and Opportunities in Deep Learning Speaker: Greg Diamos (Baidu’s Silicon Valley AI Lab (SVAIL)) Date/Time/Location: Thursday, February 23rd from 11:00 – 12:00 PM in Van Leer C341 Abstract: Just this year, deep learning has fueled significant progress in computer vision, speech recognition, and natural language processing. We have… Continue reading ECE Seminar: Greg Diamos (Baidu) on “Challenges and Opportunities in Deep Learning”
ML@GT was well represented at AAAI 2017, the premiere conference on AI, held Feb 4-9, 2017 in San Francisco, CA 2017. Here are some highlights from this conference. Frank Dellaert, a professor in the Georgia Institute of Technology’s College of Computing, will receive the Association for the Advancement of Artificial Intelligence (AAAI) Classic Paper Award… Continue reading ML@GT at AAAI 2017. Some highlights