Computer Science Doctoral Dissertations

In the second part of his thesis, Ma shows how to understand and interpret the properties of embedding models for natural languages, which were learned using nonconvex optimization.Ma is an Assistant Professor of Computer Science and Statistics at Stanford University.Meta-learning is a recent innovation that holds promise to allow machines to learn with smaller datasets.

Di Martino PDF Towards Robust Dense Visual Simultaneous Localization and Mapping (SLAM), Juan Falquez PDF Natural Language Understanding: Deep Learning for Abstract Meaning Representation, William Roger Foland Jr.

PDF A Paradigm for Scalable, Transactional, and Efficient Spatial Indexes, Ning Gao PDF Parameter Dimension Reduction for Scientific Computing, Andrew Taylor Glaws PDF In-Material Processing of High Bandwidth Sensor Measurements Using Modular Neural Networks, Dana Hughes PDF Distributed and Decentralized Algorithms for Functional Programmable Matter, John Klingner PDF Program Synthesis for Software-Defined Networking, Jedidiah Mc Clurg PDF Climate Model Quality Assurance Through Consistency Testing and Error Source Identification, Daniel J.

Winning dissertations will be published in the ACM Digital Library as part of the ACM Books Series.

Chelsea Finn of the University of California, Berkeley is the recipient of the 2018 ACM Doctoral Dissertation Award for her dissertation, “Learning to Learn with Gradients.” In her thesis, Finn introduced algorithms for meta-learning that enable deep networks to solve new tasks from small datasets, and demonstrated how her algorithms can be applied in areas including computer vision, reinforcement learning and robotics.

Beckett’s dissertation describes new principles, algorithms and tools for substantially improving the reliability of modern networks.

In the first half of his thesis, Beckett shows that it is unnecessary to simulate the distributed algorithms that traditional routers implement—a process that is simply too costly—and that instead, one can directly verify the stable states to which such algorithms will eventually converge.

He received a Ph D in Computer Science from Princeton University and a BS in Computer Science from Tsinghua University.

Chelsea Finn of University of California, Berkeley has received ACM's 2018 Doctoral Dissertation Award for introducing algorithms for meta-learning that enable deep networks to solve new tasks from small datasets.

Milroy PDF Techniques to Leverage RF Signals for Context Sensing, Phuc Van Nguyen PDF Design and Empirical Evaluation of Interactive and Interpretable Machine Learning, Forough Poursabzi-Sangdeh PDF Scalable and Timely Detection of Cyberbullying in Online Social Networks, Rahat Ibn Rafiq PDF Inductive Certificate Synthesis for Control Design, Hadi Ravanbakhsh PDF Content-Style Decomposition: Representation Discovery and Applications, Karl F.

Ridgeway PDF Measuring the Role of Visualization on Missing Values in Time Series Data, Hayeong Song PDF Analyzing Posterior Variability in Topic Models, Linzi Xing PDF Automatic Scaling of Cloud Applications via Transparently Elasticizing Virtual Memory, Ehab N.