Visual Backpropagation
This is an incremental improvement for researchers and educators seeking more accessible tools for understanding neural network training.
The authors tackled the problem of making backpropagation more transparent by implementing it in spreadsheets using declarative functional programming, resulting in a visual and transparent method called Visual Backpropagation that avoids hidden macros or procedural code.
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.