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\% $ , while the data set consists of about… Continue reading Explaining Nonparametric Regression on Low Dimensional Manifolds using Deep Neural Networks
By Min-Hung Chen, Zsolt Kira and Ghassan AlRegib Videos have become an increasingly important type of media from which we obtain valuable information and knowledge. This motivates the need for the development of video analysis techniques. The development of these techniques could, for example, provide recommendations or support discovery for different objectives. Given the recent… Continue reading Overcoming Large-scale Annotation Requirements for Understanding Videos in the Wild
The 36th International Conference on Machine Learning (ICML) is by all accounts a premier conference in the machine learning world. Thousands of papers are submitted and thousands of people from around the world travel to attend the weeklong conference. This year was no different with over 6,000 attendees and 2,473 submitted papers. Only 621 papers… Continue reading Snapshots of ICML 2019
By Sebastian Pokutta, associate director of ML@GT TL;DR: This is an informal summary of our recent paper Blended Conditional Gradients with Gábor Braun, Dan Tu, and Stephen Wright, showing how mixing Frank-Wolfe and Gradient Descent gives a new, very fast, projection-free algorithm for constrained smooth convex minimization. What is the paper about and why you might care Frank-Wolfe methods [FW]… Continue reading Mixing Frank-Wolfe and Gradient Descent
By Mark Riedl, Associate Professor at Georgia Tech On Friday, December 28th Netflix aired a special episode of their Black Mirror series called Bandersnatch. What made Bandersnatch interesting is that it was an interactive story: watchers could use a remote control to choose options at various points throughout the story’s progression to influence character choice and plot progression. (This post does not contain… Continue reading Machine Learning Meets Interactive Stories
By Yuval Pinter Imagine you’re building a boat, starting from a heap of parts. With each new board or screw, you make sure that it fits the adjacent parts, and that the material type is suitable for the section of the boat it’s in. But there are also bigger concerns to consider - is the… Continue reading How Not to Rock the Semantic Boat
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?
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
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 Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
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 What is Graph R-CNN?