This is a simple implementation of backpropagation using computational graphs. Computational Graphs are directed acyclic graphs that represent mathematical expressions and facilitate the efficient ...

paper note, including personal comments, introduction, code etc - papernote/neural network/Calculus on Computational Graphs Backpropagation.md at master · xwzhong/papernote ...

A puzzle that has long flummoxed computers and the scientists who program them has suddenly become far more manageable. A new algorithm efficiently solves the graph isomorphism problem, computer ...

We show that signal flow graph theory provides a simple way to relate two popular algorithms used for adapting dynamic neural networks, real-time backpropagation and backpropagation-through-time.

The Forward-Forward algorithm (FF) is comparable in speed to backpropagation but has the advantage that it can be used when the precise details of the forward computation are unknown.

We propose a class of neural models for graphs that do not rely on backpropagation for training, thus making learning more biologically plausible and amenable to parallel implementation in hardware.