|
Recent progress in deep generative models such as Generative Adversarial Networks (GANs) has enabled synthesizing photo-realistic images, such as faces and scenes. However, it remains much less…
name
Bolei Zhou Date
January 27th, 2021
|
|
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…
name
Jia-Bin Huang Date
December 2nd, 2020
|
|
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…
|
|
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…
name
Tiffany Deng, Deven Desai, Charles Isbell, Rapha Gontijo Lopes Date
November 20th, 2020
|
|
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…
name
Ankur Parikh Date
November 11th, 2020
|
|
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…
name
Marc Lavallee, Or Fleisher, Mint Boonyapanachoti, Lana Porter, Mark McKeague Date
October 30th, 2020
|
|
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…
name
Adriana Kovashka Date
October 28th, 2020
|
|
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…
name
Robert Nowak Date
October 7th, 2020
|
|
Modern deep learning models for natural language processing (NLP) achieve state-of-the-art predictive performance but are notoriously opaque. I will discuss recent work looking to address this…
name
Byron Wallace Date
September 9th, 2020
|
|
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…
name
Daniel Russo Date
March 11th, 2020
|
|
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…
name
Ganesh Sundaramoorthi Date
February 12th, 2020
|
|
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…
name
Niranjan Balasubramanian Date
January 15th, 2020
|
|
Learning and optimization are closely related: state-of-the-art learning problems hinge on the sophisticated design of optimizers. On the other hand, the optimization cannot be considered as…
name
Zhangyang Wang Date
November 20th, 2019
|
|
Literary novels push the limits of natural language processing. While much work in NLP has been heavily optimized toward the narrow domains of news and Wikipedia, literary novels are an entirely…
name
David Bamman Date
November 15th, 2019
|
|
Fairness in machine learning and artificial intelligence is a hot, and important topic in tech today. Join Georgia Tech faculty members Judy Hoffman, Rachel Cummings, Deven Desai, and Swati Gupta for…
name
Rachel Cummings, Swati Gupta, Judy Hoffman, Devan Desai Date
November 6th, 2019
|
|
Mailchimp is the world's largest marketing automation platform. Over a billion emails are sent by it every day, which raises the question: what exactly are users sending? We'll do a deep…
name
Muhammed Ahmed Date
October 17th, 2019
|