Search for tag: "ml@gt"

Ankur Parikh - Towards High Precision Text Generation

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…

From  Kathryn Gentilello on November 18th, 2020 3 plays 0  

Applying Emerging Technologies In Service of Journalism at The New York Times

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…

From  Kathryn Gentilello on November 5th, 2020 11 plays 0  

Adriana Kovashka - Reasoning about Complex Media from Weak Multi-modal Supervision

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…

From  Kathryn Gentilello on October 30th, 2020 0 plays 0  

Robert Nowak - Active Learning: From Linear Classifiers to Overparameterized Neural Networks

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…

From  Kathryn Gentilello on October 12th, 2020 8 plays 0  

Byron Wallace - Using rationales and influential training examples to (attempt to) explain neural predictions in NLP

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…

From  Kathryn Gentilello on September 10th, 2020 3 plays 0  

Daniel Russo - Global Optimality Guarantees for Policy Gradient Methods

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…

From  Kathryn Gentilello on March 13th, 2020 17 plays 0  

Ganesh Sundaramoorthi - Solving the Flickering Problem in Modern Convolutional Neural Networks

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…

From  Kathryn Gentilello on February 18th, 2020 30 plays 0  

Niranjan Balasubramanian - Question Answering, Event Knowledge, and other NLP Stuff: Forays into Reuse, Decomposition, and Control in Neural NLP Models

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…

From  Kathryn Gentilello on January 21st, 2020 8 plays 0  

Zhangyang Wang - Learning Augmented Optimization: Faster, Better and Guaranteed

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…

From  Kathryn Gentilello on December 4th, 2019 16 plays 0  

David Bamman - The Data-Driven Analysis of Literature

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…

From  Kathryn Gentilello on November 22nd, 2019 8 plays 0  

Rachel Cummings, Swati Gupta, Judy Hoffman, Devan Desai - A Discussion on Fairness in Machine Learning with Georgia Tech Faculty

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…

From  Kathryn Gentilello on November 14th, 2019 45 plays 0  

Muhammed Ahmed - NLP Approaches to Campaign Classification

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…

From  Kathryn Gentilello on October 30th, 2019 10 plays 0  

Ashwin Swaminathan - Perception at Magic Leap

This talk presents the importance of Computer Vision and Deep learning techniques in making Magic Leap an effective spatial computing platform. The four fundamental modalities are introduced: head…

From  Kathryn Gentilello on May 1st, 2019 55 plays 0  

Sanjeev Srivastava - AI Driven Design Approach

Design Space Exploration (DSE) is an activity that is performed to systematically analyze several design points and then select the design(s) based on parameters of interest and design requirements.…

From  Kathryn Gentilello on April 15th, 2019 6 plays 0  

Dipendra Misra - Situated Natural Language Understanding

From  Kathryn Gentilello on March 18th, 2019 30 plays 0  

Oliver Brdicka - Contextual AI - The Next Frontier Towards Human-Centric Artificial Intelligence

This talk motivates a more human-centric wave of AI, dubbed Contextual AI. Contextual AI does not refer to a specific algorithm or machine learning method - instead, it takes a human-centric view…

From  Kathryn Gentilello on March 7th, 2019 19 plays 0