Visual Backpropagation
Machine Learning
2019-06-11 v1 Programming Languages
Abstract
We show how a declarative functional programming specification of backpropagation yields a visual and transparent implementation within spreadsheets. We call our method Visual Backpropagation. This backpropagation implementation exploits array worksheet formulas, manual calculation, and has a sequential order of computation similar to the processing of a systolic array. The implementation uses no hidden macros nor user-defined functions; there are no loops, assignment statements, or links to any procedural programs written in conventional languages. As an illustration, we compare a Visual Backpropagation solution to a Tensorflow (Python) solution on a standard regression problem.
Cite
@article{arxiv.1906.04011,
title = {Visual Backpropagation},
author = {Roy S. Freedman},
journal= {arXiv preprint arXiv:1906.04011},
year = {2019}
}