Investigated the effects of floating-point error accumulation and the use of compensated summation on deep neural network training
-
Updated
Jan 9, 2026 - Jupyter Notebook
Investigated the effects of floating-point error accumulation and the use of compensated summation on deep neural network training
Compute the arithmetic mean along one or more ndarray dimensions using a two-pass error correction algorithm.
Add a description, image, and links to the compensated-summation topic page so that developers can more easily learn about it.
To associate your repository with the compensated-summation topic, visit your repo's landing page and select "manage topics."