Recent Submissions

  • Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead 

    Larochelle, Hugo (2018-10-15)
    A lot of the recent progress on many AI tasks enabled in part by the availability of large quantities of labeled data. Yet, humans are able to learn concepts from as little as a handful of examples. Meta-learning is a very ...
  • Reaching Beyond Human Accuracy With AI Datacenters 

    Diamos, Gregory (2018-10-03)
    Deep learning has enabled rapid progress in diverse problems in vision, speech, healthcare, and beyond. This progress has been driven by breakthroughs in algorithms that can harness massive datasets and powerful compute ...
  • Understanding the limitations of AI: When Algorithms Fail 

    Gebru, Timnit (2018-09-05)
    Automated decision-making tools are currently used in high stakes scenarios. From natural language processing tools used to automatically determine one’s suitability for a job, to health diagnostic systems trained to ...
  • The Natural Language Decathlon: Multitask Learning as Question Answering 

    McCann, Bryan (2018-08-28)
    Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, ...
  • Deep Learning to Learn 

    Abbeel, Pieter (Georgia Institute of Technology, 2018-08-20)
    Reinforcement learning and imitation learning have seen success in many domains, including autonomous helicopter flight, Atari, simulated locomotion, Go, robotic manipulation. However, sample complexity of these methods ...
  • Extreme scale matrix factorizations in Exploration Seismology 

    Herrmann, Felix J. (2018-04-18)
    We will present some recent work on matrix factorizations with applications that range from full-azimuth seismic data processing w/ coil acquisition to seismic data compression & recovery w/ on-the-fly data extraction, and ...
  • AI Information Session 

    Almejo, Anna; Bretan, Mason (2018-04-17)
    In this talk, we will cover general info about Samsung Research America and more specifically the research and projects happening within the Artificial Intelligence team including personal assistants, dialogue systems, ...
  • Asynchronous (Sub)gradient-Push 

    Rabbat, Mike (2018-04-04)
    We consider a multi-agent framework for distributed optimization where each agent in the network has access to a local convex function and the collective goal is to achieve consensus on the parameters that minimize the sum ...
  • The Science of Autonomy: A "Happy" Symbiosis Among Control, Learning and Physics 

    Theodorou, Evangelos A. (2018-03-28)
    In this talk I will present an information theoretic approach to stochastic optimal control and inference that has advantages over classical methodologies and theories for decision making under uncertainty. The main idea ...
  • Pruning Deep Neural Networks with Net-Trim: Deep Learning and Compressed Sensing Meet 

    Aghasi, Alireza (2018-03-14)
    We introduce and analyze a new technique for model reduction in deep neural networks. Our algorithm prunes (sparsifies) a trained network layer-wise, removing connections at each layer by addressing a convex problem. We ...
  • Data-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challenges 

    Pineau, Joelle (Georgia Institute of Technology, 2018-02-22)
    The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. In this ...
  • Do GANs Actually Learn the Distribution? 

    Arora, Sanjeev (Georgia Institute of Technology, 2018-02-22)
    Generative Adversarial Nets (GANs) is a framework for training deep generative models, due to Goodfellow et al'13. It involves a competition between a generator net that tries to produce realistic images, and a discriminator ...
  • Deep Networks for Pixel Level Inference with Applications to Medical Imaging 

    Chopra, Sumit (Georgia Institute of Technology, 2017-09-26)
  • TF-Slim: A Lightweight Library for Defining, Training and Evaluating Complex Models in TensorFlow 

    Silberman, Nathan (Georgia Institute of Technology, 2017-09-07)
    TF-Slim is a TensorFlow-based library with various components. These include modules for easily defining neural network models with few lines of code, routines for training and evaluating such models in a highly distributed ...
  • An overview of deep learning frameworks and an introduction to PyTorch 

    Chintala, Soumith (2017-09-06)
    In this talk, you will get an exposure to the various types of deep learning frameworks – declarative and imperative frameworks such as TensorFlow and PyTorch. After a broad overview of frameworks, you will be introduced ...
  • Sum-Product Networks: The Next Generation of Deep Models 

    Domingos, Pedro (2017-04-19)
    The two main types of deep learning are function approximation and probability estimation. Function approximators like convolutional neural networks are robust and allow for real-time inference, but are very inflexible, ...
  • The New Machine Leaming Center at GA Tech: Plans end Aspirations 

    Essa, Irfan (Georgia Institute of Technology, 2017-03-01)
    The Interdisciplinary Research Center (IRC) for Machine Learning at Georgia Tech (ML@GT) was established in Summer 2016 to foster research and academic activities in and around the discipline of Machine Learning. This ...