Dissertation Defenses

Data-driven Solutions for Blood Glucose Management

Enabling Practical Deployments of Privacy-Preserving Technologies

Sequential Decision Making for Large Scale Machine Learning

Efficient and Dependable Deep Learning Systems

Theory of Mind in Collaborative Tasks between Embodied Agents

Towards Generalizable Neural Networks for Graph Applications

Acceleration Techniques of Sparse Linear Algebra on Emerging Architectures

Building User-Driven Edge Devices

Optimizing Emerging Graph Applications Using Hardware-Software Co-Design

Efficient, Reconfigurable, and QoS-Aware Systems for Deep Neural Networks

Compiler Support for Robust and High Performance Autonomous Driving Environments

Securing Connected and Automated Vehicle through Proactive Vulnerability Analysis and Security Enhancement

In-SRAM Computing for Neural Network Acceleration

Automating the Verification of Distributed Systems

Bringing Practical Security to Vehicles

A Cognitive Architecture Realization of Event Cognition Capabilities

Efficient utilization of heterogeneous compute and memory systems

Towards Human Action Understanding in Social Media Videos using Multimodal Models

Sample-Efficient Algorithms for Hard-Exploration Problems in Reinforcement Learning

Learning General and Correct Procedural Knowledge in a Cognitive Architecture

Integrating visualization grammars with the task language of data analysts

Toward Practical Application-Aware Big Data Systems

Modeling Trading Strategies in Financial Markets with Data, Simulation, and Deep Reinforcement Learning

Advances in Deep Reinforcement Learning: Intrinsic Rewards, Temporal Credit Assignment, State Representations, and Value-equivalent Models

Improving Application Connectivity with Network-conscious Systems

Assessment of Privacy Risks in Mobile and Web Applications

Application-Aware Scheduling in Deep Learning Software Stacks

Dynamic Connectivity, Hopsets, and Byzantine Agreement

Advancing Digital Safety for High-Risk Communities

The Value Equivalence Principle for Model-Based Reinforcement Learning

Context-Aware Detection and Resolution of Data Anomalies for Semi-Autonomous Cyber-Physical Systems

On Addressing the Problem of Discovery for Reinforcement Learning

Augmenting Structure with Text for Improved Graph Learning

Predictable Performance and Low Cost for Geo-Distributed Applications

Constructing Meaning, Piece by Piece: A Computational Cognitive Model of Human Sentence Comprehension

Towards Free, Open, and Ubiquitous Hardware Design

Incorporating Expert Interpretation and Reasoning to Guide Model Selection in Machine Learning

In-Memory Acceleration for General Data Parallel Applications

Improving Mobile Internet Performance with Cross-Device Network Transport and Cross-Layer Application Adaptation