Search for tag: "machine learning"

Reuth Mirsky - The Seeing Eye Robot: Developing a Human-Aware Artificial Collaborator

Automated care systems are becoming more tangible than ever: recent breakthroughs in robotics and machine learning can be used to address the need for automated care created by the increasing aging…

From  Katie Gentilello 6 plays 0  

Arthur Gretton – Generalized Energy-Based Models

Arthur Gretton will describe Generalized Energy Based Models (GEBM) for generative modeling. These models combine two trained components: a base distribution (generally an implicit model, as in a…

From  Katie Gentilello 32 plays 0  

Francis Bach - Structured Prediction - Beyond Support Vector Machine and Cross Entropy

Many classification tasks in machine learning lie beyond the classical binary and multi-class classification settings. In those tasks, the output elements are structured objects made of…

From  Katie Gentilello 9 plays 0  

Alekh Agarwal - Towards a Theory of Representation Learning for Reinforcement Learning

Provably sample-efficient reinforcement learning from rich observational inputs remains a key open challenge in research. While impressive recent advances have allowed the use of linear modelling…

From  Katie Gentilello 25 plays 0  

Jie Tan - Learning Locomotion: From Simulation to Real World

Deep Reinforcement Learning (DRL) holds the promise of designing complex robotic controllers automatically. In this talk, I will discuss two different approaches to apply deep reinforcement learning…

From  Katie Gentilello 6 plays 0  

Qi Wei - Generative models based on point processes for financial time series simulation

In this seminar, I will talk about generative models based on point processes for financial time series simulation. Specifically, we focus on a recently developed state-dependent Hawkes (sdHawkes)…

From  Katie Gentilello 4 plays 0  

Ellie Pavlick - You can lead a horse to water...: Representing vs. Using Features in Neural NLP

A wave of recent work has sought to understand how pretrained language models work. Such analyses have resulted in two seemingly contradictory sets of results. On one hand, work based on…

From  Katie Gentilello 13 plays 0  

Csaba Szepesvari - Compressed computation of good policies in large MDPs

Markov decision processes (MDPs) is a framework that captures keys aspect of many real-world decision making problems with the few assumptions. Unfortunately, as a result MDPs lack structure and as…

From  Katie Gentilello 22 plays 0  

Bolei Zhou - Interpretable latent space and inverse problem in deep generative models

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…

From  Katie Gentilello 35 plays 0  

Jia-Bin Huang - Bringing Visual Memories to Life

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…

From  Katie Gentilello 24 plays 0  

ML@GT Lab presents LAB LIGHTNING TALKS 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…

From  Katie Gentilello 26 plays 0  

Let's Talk About Bias and Diversity in Data, Software, and Institutions

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…

From  Katie Gentilello 18 plays 0  

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  Katie Gentilello 16 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  Katie Gentilello 15 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  Katie Gentilello 8 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  Katie Gentilello 36 plays 0