3 papers
cs.NE2026
Backpropagation as a Nilpotent Linear System
Ahmed Boughammoura
Backpropagation is the computational engine of deep learning, yet its mathematical structure is typically treated as a procedural traversal of computational graphs. We present a gl…
cs.LG2024
Learning by the F-adjoint
Ahmed Boughammoura
A recent paper by Boughammoura (2023) describes the back-propagation algorithm in terms of an alternative formulation called the F-adjoint method. In particular, by the F-adjoint a…
cs.NE2023
Backpropagation and F-adjoint
Ahmed Boughammoura
This paper presents a concise mathematical framework for investigating both feed-forward and backward process, during the training to learn model weights, of an artificial neural n…