Active Learning Pipeline for Brain Mapping in a High Performance Computing Environment
Name
2006.14684.pdf
Description
Submitted version
Size
877.32 KB
Format
Adobe PDF
Checksum (MD5)
37299228f846ae81fea2d681633a3f3b
Author(s)
Michaleas, Adam
Gjesteby, Lars A.
Snyder, Michael
Chavez, David
Ash, Meagan
Melton, Matthew A.
Lamb, Damon G.
Burke, Sara N.
Otto, Kevin J.
Kamentsky, Lee
Date Issued
September 22, 2020
Journal
2020 IEEE High Performance Extreme Computing Conference, HPEC 2020
Publisher
IEEE
Citation
Michaleas, Adam, Gjesteby, Lars A., Snyder, Michael, Chavez, David, Ash, Meagan et al. 2020. "Active Learning Pipeline for Brain Mapping in a High Performance Computing Environment." 2020 IEEE High Performance Extreme Computing Conference, HPEC 2020.
Version
Original manuscript
Abstract
© 2020 IEEE. This paper describes a scalable active learning pipeline prototype for large-scale brain mapping that leverages high performance computing power. It enables high-throughput evaluation of algorithm results, which, after human review, are used for iterative machine learning model training. Image processing and machine learning are performed in a batch layer. Benchmark testing of image processing using pMATLAB shows that a 100x increase in throughput (10,000%) can be achieved while total processing time only increases by 9% on Xeon-G6 CPUs and by 22% on Xeon-E5 CPUs, indicating robust scalability. The images and algorithm results are provided through a serving layer to a browser-based user interface for interactive review. This pipeline has the potential to greatly reduce the manual annotation burden and improve the overall performance of machine learning-based brain mapping.
MIT Department
Lincoln Laboratory
Massachusetts Institute of Technology. Department of Chemical Engineering
Picower Institute for Learning and Memory
Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/hpec43674.2020.9286225
