Search
Now showing items 1-10 of 11
Global Optimality Guarantees for Policy Gradient Methods
(2020-03-11)
Policy gradients methods are perhaps the most widely used class of reinforcement learning algorithms. These methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a ...
ML@GT Lab presents LAB LIGHTNING TALKS 2020
(2020-12-04)
Labs affiliated with the Machine Learning Center at Georgia Tech (ML@GT) will have the opportunity to share their research interests, work, and unique aspects of their lab in three minutes or less to interested graduate ...
Let’s Talk about Bias and Diversity in Data, Software, and Institutions
(2020-11-20)
Bias and lack of diversity have long been deep-rooted problems across industries. We discuss how these issues impact data, software, and institutions, and how we can improve moving forward. The panel will feature thought ...
Towards High Precision Text Generation
(2020-11-11)
Despite large advances in neural text generation in terms of fluency, existing generation techniques are prone to hallucination and often produce output that is unfaithful or irrelevant to the source text. In this talk, ...
Solving the Flickering Problem in Modern Convolutional Neural Networks
(2020-02-12)
Deep Learning has revolutionized the AI field. Despite this, there is much progress needed to deploy deep learning in safety critical applications (such as autonomous aircraft). This is because current deep learning ...
Reasoning about Complex Media from Weak Multi-modal Supervision
(2020-10-28)
In a world of abundant information targeting multiple senses, and increasingly powerful media, we need new mechanisms to model content. Techniques for representing individual channels, such as visual data or textual data, ...
Bringing Visual Memories to Life
(2020-12-02)
Photography allows us to capture and share memorable moments of our lives. However, 2D images appear flat due to the lack of depth perception and may suffer from poor imaging conditions such as taking photos through ...
Applying Emerging Technologies In Service of Journalism at The New York Times
(2020-10-30)
Emerging technologies, particularly within computer vision, photogrammetry, and spatial computing, are unlocking new forms of storytelling for journalists to help people understand the world around them. In this talk, ...
Active Learning: From Linear Classifiers to Overparameterized Neural Networks
(2020-10-07)
The field of Machine Learning (ML) has advanced considerably in recent years, but mostly in well-defined domains using huge amounts of human-labeled training data. Machines can recognize objects in images and translate ...
Question Answering, Event Knowledge, and other NLP Stuff: Forays into Reuse, Decomposition, and Control in Neural NLP Models
(2020-01-15)
In this three-part talk, I will present some of our recent efforts that aim to control and adapt neural models to work more effectively in target applications. The first part will focus on how to repurpose a pre-trained ...