Inverse Problems and Machine Learning
The informal biweekly seminar will be meeting on Wednesdays from noon till
1pm in Blocker Rm. 627. It will be devoted to discussing mathematical
and statistical issues of inverse problems.
Image: An example of a CT head scan (courtesy of Wikipedia).

Date Time 
Location  Speaker 
Title – click for abstract 

01/29 Noon 
BLOC 628 
Mauricio Tano Department of Nuclear Engineering, Texas A&M University 
Artificial Neural Networks to Accelerate Radiation Transport Sweeps
Transport sweeping is a fast and efficient solution technique for solving the Sn (discrete ordinates) firstorder transport equation discretized using Discontinuous Finite Elements.
In transport sweeps, the angular flux solution is obtained for one angle and one spatial cell at a time by solving a small local system of equations. Gaussian Elimination (GE) is typically invoked to perform this task. However, GE may take up to 50% of the computing time spent in the sweeping routine. Here, we investigate the use of Machine Learning techniques to bypass assembling and solving the local system. In our approach, a shallow feedforward artificial neural network (ANN) is chosen. The architecture of the ANN is to be optimized in order to reduce the number of operations compared to the Gaussian Elimination solve, while keeping a bounded error in the solution. The resulting ANN consists of an ANN with only one hidden layer. Numerical results show that speedups of a factor 34 are attainable by training a shallow artificial neural network. 
Please send inquiries and suggestions to
Peter Kuchment