Dissertation Defenses

Automatic Quantification and Prediction of Affect in Spoken Interactions

Models and Algorithms for Human Action Understanding

Customized Systems of Deep Neural Networks for Energy Efficiency

Efficiency in Machine Learning with Focus on Deep Learning and Recommender Systems

Election Security is Harder Than You Think

Enabling and Improving Centralized Control in Network and Cyber-Physical Systems: An Application-Driven Approach

Towards the First Practical Applications of Quantum Computers

Interactional Slingshots: Providing Support Structure to User Interactions in Hybrid Intelligence Systems

Understanding and Improving the Performance of Web Page Loads

Machine Learning for Physiological Time Series: Representing and Controlling Blood Glucose for Diabetes Management

Understanding Word Embedding Stability Across Languages and Applications

Unsupervised Structural Embedding Methods for Efficient Collective Network Mining

A Parallel Tensor Network Contraction Algorithm and Its Applications in Quantum Computation

Learning to Generate 3D Training Data

Robust Deep Learning in the Open World with Lifelong Learning and Representation Learning

Learning Single-Image 3D from the Internet

Machine Learning in Adversarial Environments

Automatic Designs in Deep Neural Networks

Domain-specific Architectures for Data-intensive Applications

Efficient Belief Propagation for Perception and Manipulation in Clutter

Efficiently Finding Approximately-Optimal Queries for Improving Policies and Guaranteeing Safety

Enhancing System Transparency, Trust, and Privacy with Internet Measurement

Making and Keeping Probabilistic Commitments for Trustworthy Multiagent Coordination

Robust Scene Estimation for Goal-directed Robotic Manipulation in Unstructured Environments

Clarifying Oblique Specifications of Relational Queries

Improving Programming Support for Hardware Accelerators Through Automata Processing Abstractions