DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click
HERE to register or log in.
Accession Number:
AD1081389
Title:
Matching Component Analysis for Transfer Learning (Preprint)
Corporate Author:
The Ohio State University Columbus United States
Report Date:
2019-08-05
Abstract:
We introduce a new Procrustes-type method called matching component analysis to isolate components in data for transfer learning. Our theoretical results describe the sample complexity of this method, and we demonstrate through numerical experiments that our approach is indeed well suited for transfer learning.
Descriptive Note:
Technical Report,12 Aug 2019,12 Aug 2019
Supplementary Note:
Charles Clum PhD Proposal , 01 Jan 0001, 01 Jan 0001,
Pages:
0027
Distribution Statement:
Approved For Public Release;
Contract Number:
FA9550-15-F-0001
File Size:
1.25MB
