Poster 27: Andrew Falkowski – Quantifying Uncertainty in Bulk Modulus 
Predictions Using Bayesian Neural Networks

<< Return to the Virtual URS Main Page

Faculty mentor: Taylor Sparks

Machine learning is being used in materials science to accelerate the design and discovery of novel materials for advanced applications. Two Bayesian neural networks were developed to quantify uncertainty in predicting bulk modulus. These were shown to perform well compared with traditional ML approaches and accurately calculate uncertainty. This research is valuable to experimentalists who rely on uncertainty estimates to make informed decisions when synthesizing new materials.

Click below to hear me present my poster!
Click on the social media icons above to share this page.
Questions or comments? Contact me at: u0989347@utah.edu

<< Return to the Virtual URS Main Page