Appraisal of Machine Learning Evaluation Techniques in the Context of Glacier-Generated Events

We seek to improve the automated identification of glacier generated events. Specifically, we plan to explore a range of unsupervised machine learning methods and then investigate and develop robust statistical approaches to evaluating their outputs. The input to the machine learning methods will be data generated from seismic monitoring of large glaciers. We hope to improve the quality of interpretations that can be drawn from this data.

Alex Oakley

University of Tasmania

Alex Oakley is a recent graduate from the University of Tasmania. He majored in applied maths and statistics, and is enthusiastic about creating tools and knowledge that might make life more wonderful. Besides mathematics, Alex’s studies have included a mix of psychology, biology, and computer science. He plans to use this education to explore the fields of cognition and artificial intelligence. Besides the obvious potential impact on the wonderfulness of life, advancing these fields also sounds like a really interesting thing to do.

You may be interested in

Thomas McCarthy McCann

Thomas McCarthy McCann

Nexus Between Randomised Numerical Linear Algebra and Big Time Series Data
Sean McGowan

Sean McGowan

PDE Discovery Using Machine Learning
Stephanie Fuser

Stephanie Fuser

Global Sensitivity Analysis of a Model for Cyprinid Herpes Virus 3 as a Biocontrol Agent of Common Carp
Will Veenman

Will Veenman

Determining the Metric Dimension of Random Regular Graphs
Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text.