Skip to main content
. Author manuscript; available in PMC: 2021 Nov 5.
Published in final edited form as: Int Conf Big Data Smart Comput. 2021 Mar 10;2021:10.1109/bigcomp51126.2021.00021. doi: 10.1109/bigcomp51126.2021.00021

Fig. 1.

Fig. 1.

A. Simultaneous random subsampling of examples (rows in red) and features (columns in yellow) without replacement from the original data matrix yields a “minipatch” (orange). B. The same minipatch in A is a random submatrix of the data matrix after a permutation. C. Minipatch learning is an ensemble of learners trained on many random minipatches.