ML@GT Seminar Series

Series Type
Event Series
Associated Organizations
Associated Organizations
Organizational Unit
Organizational Unit

Publication Search Results

Now showing 1 - 10 of 52
  • Item
    AI Driven Design Approach
    ( 2019-04-03) Srivastava, Sanjeev ; Machine Learning Center ; College of Computing
    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. For complex systems, design engineers spend a lot of time generating new design iterations using simulation-based tools. However, they do not explore the complete design space due to time-consuming design creation and analyses process, and hence do not generate optimal design but rather settle for a sub-optimal design that meets the requirements. Recently, there have been advances in the areas of Artificial Intelligence (AI), cognitive computing, Internet of Things, 3D printing, advanced robotics, that provide capabilities to transform the current design process by automating various design steps, speeding up the design and analysis toolchain, and creative decision making. Within Siemens CT we have been developing a Generative Design framework, which utilizes the AI and knowledge representation techniques in combination with traditional design methods to generate better designs in a faster manner. The talk will address various technical areas of this framework and the various AI methods which we are currently applying to optimally design parts, systems, and processes.
  • Item
    The Statistical Foundations of Learning to Control
    ( 2018-11-14) Recht, Benjamin ; Machine Learning Center ; College of Computing
    Given the dramatic successes in machine learning and reinforcement learning over the past half decade, there has been a surge of interest in applying these techniques to continuous control problems in robotics and autonomous vehicles. Though such control applications appear to be straightforward generalizations of standard reinforcement learning, few fundamental baselines have been established prescribing how well one must know a system in order to control it. In this talk, I will discuss how one might merge techniques from statistical learning theory with robust control to derive such baselines for such continuous control. I will explore several examples that balance parameter identification against controller design and demonstrate finite sample tradeoffs between estimation fidelity and desired control performance. I will describe how these simple baselines give us insights into shortcomings of existing reinforcement learning methodology. I will close by listing several exciting open problems that must be solved before we can build robust, safe learning systems that interact with an uncertain physical environment.
  • Item
    Situated Natural Language Understanding
    ( 2019-03-08) Misra, Dipendra ; Machine Learning Center ; College of Computing
  • Item
    Data-to-Decisions for Safe Autonomous Flight
    (Georgia Institute of Technology, 2018-11-07) Atkins, Ella ; Machine Learning Center ; College of Computing ; Institute for Robotics and Intelligent Machines
    Traditional sensor data can be augmented with new data sources such as roadmaps and geographical information system (GIS) Lidar/video to offer emerging unmanned aircraft systems (UAS) and urban air mobility (UAM) a new level of situational awareness. This presentation will summarize my group’s research to identify, process, and utilize GIS, map, and other real-time data sources during nominal and emergency flight planning. Specific efforts have utilized machine learning to automatically map flat rooftops as urban emergency landing sites, incorporate cell phone data into an occupancy map for risk-aware flight planning, and extend airspace geofencing into a framework capable of managing all traffic types in complex airspace and land-use environments. The presentation will end with videos illustrating recent work to experimentally validate the continuum deformation cooperative control strategy in the University of Michigan’s new M-Air netted flight facility.
  • Item
    The Seeing Eye Robot: Developing a Human-Aware Artificial Collaborator
    ( 2021-10-27) Mirksy, Reuth ; Machine Learning Center ; College of Computing
    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 population. However, such systems require overcoming several technological, ethical, and social challenges. One inspirational manifestation of these challenges can be observed in the training of seeing-eye dogs for visually impaired people. A seeing-eye dog is not just trained to obey its owner, but also to “intelligently disobey”: if it is given an unsafe command from its handler, it is taught to disobey it or even insist on a different course of action. This paper proposes the challenge of building a seeing-eye robot, as a thought-provoking use-case that helps identify the challenges to be faced when creating behaviors for robot assistants in general. Through this challenge, this paper delineates the prerequisites that an automated care system will need to have in order to perform intelligent disobedience and to serve as a true agent for its handler.
  • Item
    A Discussion on Fairness in Machine Learning with Georgia Tech Faculty
    ( 2019-11-06) Cummings, Rachel ; Desai, Devan ; Gupta, Swati ; Hoffman, Judy ; Machine Learning Center ; College of Computing ; Georgia Institute of Technology. Scheller College of Business ; Georgia Institute of Technology. School of Interactive Computing
    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 a panel discussion on their work in regards to fairness and their motivations behind it. Sponsored by the Machine Learning Center at Georgia Tech.
  • Item
    The Data-Driven Analysis of Literature
    ( 2019-11-15) Bamman, David ; Machine Learning Center ; College of Computing
    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 different animal--the long, complex sentences in novels strain the limits of syntactic parsers with super-linear computational complexity, their use of figurative language challenges representations of meaning based on neo-Davidsonian semantics, and their long length (ca. 100,000 words on average) rules out existing solutions for problems like coreference resolution that expect a small set of candidate antecedents. At the same time, fiction drives computational research questions that are uniquely interesting to that domain. In this talk, I'll outline some of the opportunities that NLP presents for research in the quantitative analysis of culture--including measuring the disparity in attention given to characters as a function of their gender over two hundred years of literary history (Underwood et al. 2018)--and describe our progress to date on two problems essential to a more complex representation of plot: recognizing the entities in literary texts, such as the characters, locations, and spaces of interest (Bamman et al. 2019) and identifying the events that are depicted as having transpired (Sims et al. 2019). Both efforts involve the creation of a new dataset of 200,000 words evenly drawn from 100 different English-language literary texts and building computational models to automatically identify each phenomenon. This is joint work with Matt Sims, Ted Underwood, Sabrina Lee, Jerry Park, Sejal Popat and Sheng Shen.
  • Item
    Pruning Deep Neural Networks with Net-Trim: Deep Learning and Compressed Sensing Meet
    ( 2018-03-14) Aghasi, Alireza ; Machine Learning Center ; College of Computing
    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 present both parallel and cascade versions of the algorithm along with the mathematical analysis of the consistency between the initial network and the retrained model. We also discuss an ADMM implementation of Net-Trim, easily applicable to large scale problems. In terms of the sample complexity, we present a general result that holds for any layer within a network using rectified linear units as the activation. If a layer taking inputs of size N can be described using a maximum number of s non-zero weights per node, under some mild assumptions on the input covariance matrix, we show that these weights can be learned from O(slog N/s) samples.
  • Item
    Automated Perception in the Real World: The Problem of Scarce Data
    ( 2018-11-30) Ernst, Jan ; Machine Learning Center ; College of Computing
    Machine perception is a key step toward artificial intelligence in domains such as self-driving cars, industrial automation, and robotics. Much progress has been made in the past decade, driven by machine learning, ever-increasing computational power, and the reliance on (seemingly) vast data sets. There are however critical issues in translating academic progress into the real world: available data sets may not match real-world environments well, and even if they are abundant and matching well, then interesting samples from a real-world perspective may be exceedingly rare and thus still be too sparsely represented to learn from directly. In this talk, I illustrate how we have approached this problem strategically as an example of industrial R&D from inception to product. I will also go in-depth on an approach to automatically infer previously unseen data by learning compositional visual concepts via mutual cycle consistency.
  • Item
    Reasoning about Complex Media from Weak Multi-modal Supervision
    ( 2020-10-28) Kovashka, Adriana ; Machine Learning Center ; College of Computing
    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 data or textual data, have greatly improved, and some techniques exist to model the relationship between channels that are “mirror images” of each other and contain the same semantics. However, multimodal data in the real world contains little redundancy; the visual and textual channels complement each other. We examine the relationship between multiple channels in complex media, in two domains, advertisements and political articles. First, we collect a large dataset of advertisements and public service announcements, covering almost forty topics (ranging from automobiles and clothing, to health and domestic violence). We pose decoding the ads as automatically answering the questions “What should do viewer do, according to the ad” (the suggested action), and “Why should the viewer do the suggested action, according to the ad” (the suggested reason). We train a variety of algorithms to choose the appropriate action-reason statement, given the ad image and potentially a slogan embedded in it. The task is challenging because of the great diversity in how different users annotate an ad, even if they draw similar conclusions. One approach mines information from external knowledge bases, but there is a plethora of information that can be retrieved yet is not relevant. We show how to automatically transform the training data in order to focus our approach’s attention to relevant facts, without relevance annotations for training. We also present an approach for learning to recognize new concepts given supervision only in the form of noisy captions. Second, we collect a dataset of multimodal political articles containing lengthy text and a small number of images. We learn to predict the political bias of the article, as well as perform cross-modal retrieval despite large visual variability for the same topic. To infer political bias, we use generative modeling to show how the face of the same politician appears differently at each end of the political spectrum. To understand how image and text contribute to persuasion and bias, we learn to retrieve sentences for a given image, and vice versa. The task is challenging because unlike image-text in captioning, the images and text in political articles overlap in only a very abstract sense. We impose a loss requiring images that correspond to similar text to live closeby in a projection space, even if they appear very diverse purely visually. We show that our loss significantly improves performance in conjunction with a variety of existing recent losses. We also propose new weighting mechanisms to prioritize abstract image-text relationships during training.