Publications
-
GPU Performance Prediction using Representation Learning
We propose a representation learning approach to address the high level of contention among thousands of parallel threads in GPU activity prediction models.
-
Connected Freight Rail Stock: A Modular Approach Integrating Sensors, Actors and Cyber Physical Systems for Operational Advantages and Condition Based Maintenance
This paper describes the basis of such a system including the power supply, intra-train communications, sensing and cloud-based analytics.
-
Low Precision Neural Networks using Subband Decomposition
In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase.
-
Achieving Differential Privacy in Secure Multiparty Data Aggregation Protocols on Star Networks
We consider the problem of privacy-preserving data aggregation in a star network topology, i.e., several untrusting participants connected to a single aggregator.
-
Transient electronics based on frangible stress-engineered glass substrates
We present an approach to transience electronics where transience is achieved by fracturing electronic components into small pieces and widely dispersing the fragments over a large area.
-
Mapping the Hypocretin/Orexin Neuronal System: An Unexpectedly Productive Journey
Early in 1998, we (and others) described the same hypothalamic neuropeptides, respectively called the hypocretins or orexins, which were discovered using two different approaches.
-
Measuring Student Learning in Introductory Block-Based Programming: Examining Misconceptions of Loops, Variables, and Boolean Logic
This research aims to develop assessment items for measuring student understanding in introductory CS classrooms in middle school using a principled approach for assessment design.
-
Learner Modeling for Adaptive Scaffolding in a Computational Thinking-Based Science Learning Environment
We develop a learner modeling and adaptive scaffolding framework for CTSiM –an open ended learning environment that supports synergistic learning of science and Computational Thinking for middle school students.
-
Impact of the National Writing Project’s College-Ready Writers Program in High-Need Rural Districts
This paper reports on a district-randomized controlled trial of the National Writing Project’s College-Ready Writers Program (CRWP), implemented in high-need rural districts in 10 states.
-
Joint modeling of articulatory and acoustic spaces for continuous speech recognition tasks
This paper investigates using deep neural networks (DNN) and convolutional neural networks (CNNs) for mapping speech data into its corresponding articulatory space.
-
Access & Equity in Linked Learning: A Report on Pathway Access and Academic Outcomes for Traditionally Underserved Students
This brief describes the successes and challenges the districts have experienced in fostering access and equity in Linked Learning pathways, examining five groups of students frequently underserved by traditional schools.
-
Analysis and prediction of heart rate using speech features from natural speech
We predict HR from speech using the SRI BioFrustration Corpus.In contrast to previous studies we use continuous spontaneous speech as input.