Georgia Tech Interdisciplinary Research Centers (IRCs)
All materials in SMARTech are protected under U.S. Copyright Law and all rights are reserved. Such materials may be used, quoted or reproduced for educational purposes only with prior permission, provided proper attribution is given. Any redistribution, reproduction or use of the materials, in whole or in part, is prohibited without prior permission of the author.
Sub-communities within this community
Recent Submissions
-
Operational and Tactical Analysis of Same-Day Delivery Distribution Systems
(2018-10-24)E-retail is a highly competitive segment that constantly demands innovation and process improvement. One such innovation rapidly gaining traction is same-day delivery (SDD); large e-retailers like Amazon are quite active ... -
Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead
(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
(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 ... -
Supply Chain Innovation Showcase
(2018-09-26)A special session where two early stage companies will talk individually about their unique characteristics/problems solved. Amari Ruff from Sudu will present "How startups are pushing the Future of Transportation" to ... -
Desired Learning Behaviors in Online Education: Measuring Student Perceptions and Practices in the OMSCS Program
(Georgia Institute of Technology, 2018-09-18)As online education continues to grow in popularity, so too do educators’ concerns about the challenges facing asynchronous learning environments. The Georgia Tech OMSCS program addresses the concerns of the education ... -
Understanding the limitations of AI: When Algorithms Fail
(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 ... -
Smart GT - Achieving Smart Communities Development at Georgia Tech
(2018-08-29)Whether measured by expected market valuation, speed of technological change, or potential of data collection and analytics, smart cities development has become a vital area of growth for governments, the public and ... -
The Natural Language Decathlon: Multitask Learning as Question Answering
(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
(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 ... -
The Atlanta Beltline: From Vision to Reality
(2018-06-21)Join Ryan Gravel of Sixpitch - whose GT master’s thesis launched the BeltLine; Odetta MacLeish- White of TransFormation Alliance; and Michael Bryan, Georgia Tech student and TransFormation Alliance intern for an engaging ... -
Extreme scale matrix factorizations in Exploration Seismology
(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
(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, ... -
Routing in the Physical Internet: Framework, Algorithms and Research Perspectives
(2018-04-06)The Physical Internet (PI) opens many more options to deliver goods to the end destination, thanks to interconnected services. To exploit such opportunities, routing algorithms must be developed at different levels to make ... -
The Design and Operation of On-Demand Distribution Systems
(2018-04-04)Modern distribution systems need to fulfill a wide variety of requests quickly with little warning in small units to many dispersed locations at low costs. This is fundamentally different than yesterday’s demand, which ... -
Asynchronous (Sub)gradient-Push
(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
(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
(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 ... -
What Does Sustainability Have to Do with Happiness?
(2018-02-28)Dr. Scott Cloutier shares his work developing the Sustainability through Happiness Framework and Sustainable Neighborhoods for Happiness™ (SNfH) project. He, his students, and team use a participatory, neighborhood-based ... -
Data-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challenges
(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?
(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 ...
RSS 1.0