myUNB News
News for Faculty and Staff

Physics Seminar - Is Artificial Neural Network A Silver Bullet for Exponential Analysis?

Author: Penny Davenport

Posted on Oct 29, 2019

Category: News and Notices

The next UNBF Physics Department Seminar will be held on Thursday, Oct. 31, from 1:15 - 2:15 p.m., in the IUC Physics Admin Bldg, 204.

Dan Xiao, University of Windsor, will discuss, "Is Artificial Neural Network A Silver Bullet for Exponential Analysis?"

“Exponential analysis is required in numerous areas of physics, such as fluorescence decay analysis, semiconductor deep level transient spectroscopy, radioactive decays, and nuclear magnetic resonance (NMR). However, it is non-trivial to recover the decay constants and amplitudes from experimental data. Conventional inversion methods require a large number of data points with high signal-to-noise ratio, which are not readily available in many applications. Artificial neural networks (ANNs) are a series of densely connected information processing nodes which cumulatively map a set of inputs to some features. They have proven to be universal approximators and powerful tools for solving complex nonlinear problems. I will present our recent work employing ANNs in the context of quantitative NMR transverse relaxation time analysis, including advantages over conventional methods and potential pitfalls.”

Category: News and Notices

Article Contact Information

Contact: Penny Davenport

Email Address: