Small Data Challenge: Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size
Rhett N. D’souza, Po-Yao Huang, Fang-Cheng Yeh
This paper investigates how network structure affects performance in small data settings and finds that optimal structure is data-driven, not sample size-driven.
bioRxiv · Aug 28, 2018 · PreprintBioengineering