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

Huge 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 →

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 →

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 →

Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance

By: Prithvijit Chattopadhyay and Ramprasaath R. Selvaraju (Paper authors include Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, and Stefan Lee) Deep Neural Networks have pushed the boundaries of standard image-classification tasks in the past few years, with performance on many challenging benchmarks reaching near human-level accuracies. One of the... Continue Reading →

What is Graph R-CNN?

By Jianwei Yang and Jiasen Lu The following post breaks down Graph R-CNN for Scene Graph Generation, which will be presented at the European Conference on Computer Vision 2018 (ECCV). The conference takes place September 8th through 14th in Munich, Germany.  Visual scene understanding has traditionally focused on identifying objects in images -- learning to predict their... Continue Reading →

SHIELD: Defending Deep Neural Networks from Adversarial Attacks

by Nilaksh Das, PhD student at Georgia Institute of Technology in the School of Computational Science and Engineering. Das is advised by Polo Chau. “SHIELD is a fast and practical approach to defend deep neural networks from adversarial attacks. This work proposes a multifaceted framework which incorporates compression, randomization, model-retraining, and ensembling to make computer vision models robust to adversarial... Continue Reading →

Create a website or blog at WordPress.com

Up ↑

%d bloggers like this: