Search for tag: "machine learning"

76 Media

01:01:46 Qi Wei - Generative models based on point… Qi Wei - Generative models based on point processes for financial time series simulation	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)… ml@gt seminar series machine learning georgia tech spring 2021 From Katie Gentilello on April 22nd, 2021 3 plays 0 name Qi Wei Date April 7th, 2021
57:06 Ellie Pavlick - You can lead a horse to water...:… Ellie Pavlick - You can lead a horse to water...: Representing vs. Using Features in Neural NLP	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… ml@gt seminar series machine learning georgia tech spring 2021 From Katie Gentilello on April 1st, 2021 9 plays 0 name Ellie Pavlick Date March 24th, 2021
01:07:52 Csaba Szepesvari - Compressed computation of good… Csaba Szepesvari - Compressed computation of good policies in large MDPs	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… ml@gt seminar series machine learning georgia tech spring 2021 From Katie Gentilello on March 11th, 2021 16 plays 0 name Csaba Szepesvari Date March 10th, 2021
52:11 Bolei Zhou - Interpretable latent space and… Bolei Zhou - Interpretable latent space and inverse problem in deep generative models	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… ml@gt seminar series machine learning georgia tech spring 2021 From Katie Gentilello on February 10th, 2021 18 plays 0 name Bolei Zhou Date January 27th, 2021
57:05 Jia-Bin Huang - Bringing Visual Memories to Life Jia-Bin Huang - Bringing Visual Memories to Life	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on December 9th, 2020 16 plays 0 name Jia-Bin Huang Date December 2nd, 2020
01:14:20 ML@GT Lab presents LAB LIGHTNING TALKS 2020 ML@GT Lab presents LAB LIGHTNING TALKS 2020	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on December 9th, 2020 16 plays 0 Date December 4th, 2020
54:00 Let's Talk About Bias and Diversity in Data,… Let's Talk About Bias and Diversity in Data, Software, and Institutions	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… ml@gt seminar series georgia tech fall 2020 machine learning From Katie Gentilello on November 30th, 2020 11 plays 0 name Tiffany Deng, Deven Desai, Charles Isbell, Rapha Gontijo Lopes Date November 20th, 2020
53:26 Ankur Parikh - Towards High Precision Text… Ankur Parikh - Towards High Precision Text Generation	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on November 18th, 2020 12 plays 0 name Ankur Parikh Date November 11th, 2020
01:22:08 Applying Emerging Technologies In Service of… Applying Emerging Technologies In Service of Journalism at The New York Times	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on November 5th, 2020 13 plays 0 name Marc Lavallee, Or Fleisher, Mint Boonyapanachoti, Lana Porter, Mark McKeague Date October 30th, 2020
01:00:01 Adriana Kovashka - Reasoning about Complex Media… Adriana Kovashka - Reasoning about Complex Media from Weak Multi-modal Supervision	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on October 30th, 2020 6 plays 0 name Adriana Kovashka Date October 28th, 2020
01:10:17 Robert Nowak - Active Learning: From Linear… Robert Nowak - Active Learning: From Linear Classifiers to Overparameterized Neural Networks	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… ml@gt seminar series machine learning fall 2020 georgia tech From Katie Gentilello on October 12th, 2020 22 plays 0 name Robert Nowak Date October 7th, 2020
01:00:14 Byron Wallace - Using rationales and influential… Byron Wallace - Using rationales and influential training examples to (attempt to) explain neural predictions in NLP	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… ml@gt seminar series machine learning georgia tech fall 2020 From Katie Gentilello on September 10th, 2020 6 plays 0 name Byron Wallace Date September 9th, 2020
59:17 Daniel Russo - Global Optimality Guarantees for… Daniel Russo - Global Optimality Guarantees for Policy Gradient Methods	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… machine learning ml@gt seminar series georgia tech recorded by gtlibrary spring 2020 From Katie Gentilello on March 13th, 2020 23 plays 0 name Daniel Russo Date March 11th, 2020
49:16 Ganesh Sundaramoorthi - Solving the Flickering… Ganesh Sundaramoorthi - Solving the Flickering Problem in Modern Convolutional Neural Networks	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… machine learning ml@gt seminar series georgia tech recorded by gtlibrary spring 2020 From Katie Gentilello on February 18th, 2020 43 plays 0 name Ganesh Sundaramoorthi Date February 12th, 2020
57:29 Niranjan Balasubramanian - Question Answering,… Niranjan Balasubramanian - Question Answering, Event Knowledge, and other NLP Stuff: Forays into Reuse, Decomposition, and Control in Neural NLP Models	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… ml@gt seminar series machine learning georgia tech recorded by gtlibrary spring 2020 From Katie Gentilello on January 21st, 2020 8 plays 0 name Niranjan Balasubramanian Date January 15th, 2020
01:07:36 Zhangyang Wang - Learning Augmented Optimization:… Zhangyang Wang - Learning Augmented Optimization: Faster, Better and Guaranteed	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… ml@gt seminar series machine learning georgia tech recorded by gtlibrary fall 2019 From Katie Gentilello on December 4th, 2019 25 plays 0 name Zhangyang Wang Date November 20th, 2019