NIRS Automated Machine Learning (NAML), is a system that automates the running of time series machine learning algorithms on neural data [1]. This project expanded NAML by adding seven new algorithms, implementing manifold validation, and giving the user the ability to balance their datasets. NAML 2.0 gives more precise results than its predecessor and can still be utilized without expertise in machine learning. NAML 2.0 will allow researchers to classify brain states quickly, easily, and consistently. NAML 2.0 has been benchmarked on neural data for both accuracy and speed.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Buntel, Ellery

Subject

• Computing
• Innovation

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-121120-141220
• 5016

Keyword

• Machine Learning
• Python
• Computer Science
• BCI
• Neuroscience

Advisor

• Neamtu, Rodica
• Solovey, Erin

Year

• 2020

Date created

• 2020-12-11

Resource type

• Major Qualifying Project

Major

• Computer Science

Rights statement

• In Copyright

License

• All rights reserved