Experimental Design for Bathymetry Editing

07/15/2020

∙

by   Julaiti Alafate, et al.

∙

11

∙

share

We describe an application of machine learning to a real-world computer assisted labeling task. Our experimental results expose significant deviations from the IID assumption commonly used in machine learning. These results suggest that the common random split of all data into training and testing can often lead to poor performance.