Skip to Main Content U.S. Department of Energy
Deep Science Agile Initiative

Publications

2018

MILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Properties from Chemical Text Representations
[+expand/-collapse]

Using Rule-Based Models for Weak Supervised Learning: ChemNet for Transferable Chemical Property Prediction
[+expand/-collapse]

Lidar Cloud Detection with Fully Convolutional Networks
[+expand/-collapse]

A Koopman Operator Approach to Computing and Balancing Grammians for Discrete Time Nonlinear Systems
[+expand/-collapse]

Deep Learning for Scientific Discovery
[+expand/-collapse]

VULCON - A System for Vulnerability Prioritization, Mitigation, and Management
[+expand/-collapse]

The Outer Product Structure of Neural Network Derivatives
[+expand/-collapse]

ToxNet: A Multi-Modal Deep Learning Ensemble
[+expand/-collapse]

A Class of Logistic Functions for Approximating State-Inclusive Koopman Operators
[+expand/-collapse]

Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians
[+expand/-collapse]

Deep Data-Driven Stochastic Models for Characterizing the Operational Envelope of a Genetic Toggle Switch
[+expand/-collapse]

Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks
[+expand/-collapse]

Use of Neural Networks to Analyze Pulse Shape Data in Low-background Detectors
[+expand/-collapse]

Doing the Impossible: Why Neural Networks Can Be Trained at All
[+expand/-collapse]

Generative Adversarial Network based Autoencoder: Application to Fault Detection Problem for Closed Loop Dynamical Systems
[+expand/-collapse]

Fractal Dimension Calculation using Box Locality Index
[+expand/-collapse]

Protein Mutation Stability Ternary Classification using Neural Networks and Rigidity Analysis
[+expand/-collapse]

Using Rule-Based Models for Weak Supervised Learning: ChemNet for Transferable Chemical Property Prediction
[+expand/-collapse]

Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detection
[+expand/-collapse]

2017


How Much Chemistry Does Deep Learning Need to Know to Make Accurate Chemical Predictions?
[+expand/-collapse]

SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Properties from Chemical Text Representations
[+expand/-collapse]

Forecasting Influenza-like Illness Dynamics for Military Populations using Neural Networks and Social Media
[+expand/-collapse]

Using Social Media to Predict the Future: A Systematic Literature Review
[+expand/-collapse]

Studying Fish Near Ocean Energy Devices Using Underwater Video
[+expand/-collapse]

Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection
[+expand/-collapse]

Intrinsic and Extrinsic Evaluation of Spatiotemporal Text Representations in Twitter Streams
[+expand/-collapse]

Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter
[+expand/-collapse]

Uncovering the Relationships between Military Community Health and Affects Expressed in Social Media
[+expand/-collapse]

Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary
[+expand/-collapse]

Dynamic Input Structure and Network Assembly for Few-Shot Learning
[+expand/-collapse]

A Koopman Operator Approach to Computing and Balancing Grammians for Discrete Time Nonlinear Systems
[+expand/-collapse]

Beyond Fine Tuning: Adding Capacity to Leverage Few Labels
[+expand/-collapse]

Assessing the Linguistic Productivity of Unsupervised Deep Neural Networks
[+expand/-collapse]

Faster Fuzzing: Reinitialization with Deep Neural Models
[+expand/-collapse]

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation
[+expand/-collapse]

Solving Differential Equations with Unknown Constitutive Relations as Recurrent Neural Networks
[+expand/-collapse]

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction
[+expand/-collapse]

Deep Learning