Description
Deep learning is becoming a cornerstone for many applications. Finding appropriate models in the presence of data requires merging physical, computational, and statistical models. This workshop brings together experts working on mathematical, statistical, computational, and engineering aspects of deep learning to share their research experience in model learning.
The workshop will be hosted by Texas A&M University in College Station, Texas, and is supported by the Institute for Scientific Computation, Energi Simulation, Artie McFerrin Department of Chemical Engineering, and Department of Computer Science & Engineering.
Organizing Committee
- Yalchin Efendiev, Institute for Scientific Computation
- Eduardo Gildin, Energi Simulation
- Joseph Kwon, Artie McFerrin Department of Chemical Engineering
- Zhangyang (Atlas) Wang, Department of Computer Science & Engineering
Speakers
-
Ulisses Braga-Neto, Department of Electrical & Computer Engineering
- Neural Network Prediction of Dengue Fever Severity Based on Genetic Polymorphisms
-
Suman Chakravorty, Department of Aerospace Engineering
- A Decoupling Principle in Stochastic Optimal Control and Its Implications
-
Yalchin Efendiev, Department of Mathematics
- Reduced-Order Deep Learning for Flow Dynamics. The Interplay Between Deep Learning and Model Reduction
-
Eduardo Gildin, Harold Vance Department of Petroleum Engineering
- Applications of Machine Learning to Life-Cycle Reservoir Engineering: From Drilling to Reservoir Simulation
-
Boris Hanin, Department of Mathematics
- The Neural Tangent Kernel in Deep Networks
-
Shuiwang Ji, Department of Computer Science & Engineering
- Deep Learning on Images and Graphs
-
Peter Kuchment, Department of Mathematics
- Deep Learning in Detecting Illicit Nuclear Materials
-
Siddharth Misra, Harold Vance Department of Petroleum Engineering
- Applications of Machine Learning to Predict the Physical Properties of the Subsurface
-
Abhinav Narasingam, Artie McFerrin Department of Chemical Engineering
- Koopman Operator Based Model Predictive Control for Hydraulic Fracturing
-
Guni Sharon, Department of Computer Science & Engineering
- Learning an Interpretable Control Policy Through Deep Neural Networks
-
Rui Tuo, Department of Industrial & Systems Engineering
- Projection Pursuit Gaussian Process Regression
-
Zhangyang (Atlas) Wang, Department of Computer Science & Engineering
- Re-Comparing ImageNet Classifiers: Accuracy Should Not Be the Only Goal
Schedule
All workshop presentations will take place in Zachry Engineering Education Complex (ZACH) 297. Please note that the schedule is tentative and subject to change. All times listed are local time.
- –
- Welcome
- –
- Shuiwang Ji, Department of Computer Science & Engineering
- Deep Learning on Images and Graphs
- –
- Zhangyang (Atlas) Wang, Department of Computer Science & Engineering
- Re-Comparing ImageNet Classifiers: Accuracy Should Not Be the Only Goal
- –
- Break
- –
- Peter Kuchment, Department of Mathematics
- Deep Learning in Detecting Illicit Nuclear Materials
- –
- Abhinav Narasingam, Artie McFerrin Department of Chemical Engineering
- Koopman Operator Based Model Predictive Control for Hydraulic Fracturing
- –
- Lunch Break
- –
- Suman Chakravorty, Department of Aerospace Engineering
- A Decoupling Principle in Stochastic Optimal Control and Its Implications
- –
- Rui Tuo, Department of Industrial & Systems Engineering
- Projection Pursuit Gaussian Process Regression
- –
- Guni Sharon, Department of Computer Science & Engineering
- Learning an Interpretable Control Policy Through Deep Neural Networks
- –
- Boris Hanin, Department of Mathematics
- The Neural Tangent Kernel in Deep Networks
- –
- Ulisses Braga-Neto, Department of Electrical & Computer Engineering
- Neural Network Prediction of Dengue Fever Severity Based on Genetic Polymorphisms
- –
- Eduardo Gildin, Harold Vance Department of Petroleum Engineering
- Applications of Machine Learning to Life-Cycle Reservoir Engineering: From Drilling to Reservoir Simulation
- –
- Siddharth Misra, Harold Vance Department of Petroleum Engineering
- Applications of Machine Learning to Predict the Physical Properties of the Subsurface
- –
- Yalchin Efendiev, Department of Mathematics
- Reduced-Order Deep Learning for Flow Dynamics. The Interplay Between Deep Learning and Model Reduction
- –
- Closing Remarks
Contact Information
If you have any questions concerning this workshop, email Brad Shumbera at shumbera@tamu.edu.