Search
Now showing items 1-10 of 283
Learning to teach in multiagent reinforcement learning with teams of N > 2 Agents
(Massachusetts Institute of Technology, 2020)
Sharing unique insights while learning how to collectively perform a task is a central function of human intelligence in groups. While navigating a complex task independently can be feasible, communicating with and studying ...
Gaze Prediction in First-Person View Videos
(Massachusetts Institute of Technology, 2020)
Gaze is an important topic in computer vision as it reveals points of interest that tend to capture a subject's attention in a scene and potential intentions of the subject of gaze. Gaze data is becoming more readily ...
Adaptive gain spatial receiver for wide dynamic range communication links
(Massachusetts Institute of Technology, 2020)
Wireless optical communication facilitates high-speed transmission across long distances. However, time-varying and spatially-dependent attenuation through freespace channels due to scattering impedes operation for many ...
Predicting post-surgical opioid consumption using perioperative surgical data
(Massachusetts Institute of Technology, 2020)
Improper consumption of prescription opioids is a massive public health issue in the United States currently. Here, we propose one approach of tackling this issue through using machine learning techniques to predict opioid ...
A framework for computing on sparse tensors based on operator properties
(Massachusetts Institute of Technology, 2020)
Tensor operations have been traditionally limited to addition and multiplication operations. For operations of sparse tensors, theses semantics were extended to handle operating on zero values. However, there are many ...
Inference of point sources from NuSTAR X-ray observations using probabilistic cataloging
(Massachusetts Institute of Technology, 2020)
An important task in astronomy is in locating astronomical objects, known as sources, in images and describing the sources' properties such as size, spatial information, intensity, and color. This task is known as cataloging, ...
Neural physics simulation through volumetric reconstruction
(Massachusetts Institute of Technology, 2020)
In this thesis we propose a method for simulating 3D object motion given 2D image input or simplified 3D models. Our system incorporates neural networks for tasks that are otherwise complex or computationally expensive to ...
Wikum+: integrating discussion and summarization in collaborative writing
(Massachusetts Institute of Technology, 2020)
In many instances of collaborative writing, ideation and deliberation about what to write happen in a separate space from the actual document writing. However, having discussion and writing separated may result in a final ...
Roboat routing and itinerary planning for tourists
(Massachusetts Institute of Technology, 2020)
When a tourist visits a new city for a brief trip, they will often ask themselves many questions. which attractions should I visit? How should I get from one to the next? Should I stay at this point of interest longer or ...
Development of a Co-Evolution assistant to limit database decay
(Massachusetts Institute of Technology, 2020)
There is currently a lack of informational tools to guide changes to database schemas in large-scale inormation systems. In practice, schema changes are made with relatively little regard for how they will impact the ...