Metraipolis › archive › dc_4fa10ff8f537
Detailed Derivation of The Backpropagation Algorithm — arXiv:2611.02152
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02152
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:23:34.546Z
- SHA-256 of the archived text
c83b161f363c653d6fa53842f5998ca990c9061e514f2037515e98092f6fade2- Stable URL of this page
https://metraipolis.com/documento/dc_4fa10ff8f537
How to cite
Detailed Derivation of The Backpropagation Algorithm — arXiv:2611.02152 — arXiv (en), https://arxiv.org/abs/2611.02152 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fa10ff8f537 (Metraipolis archive dc_4fa10ff8f537, sha256 c83b161f363c653d6fa53842f5998ca990c9061e514f2037515e98092f6fade2)
BibTeX
@misc{dc4fa10ff8f537,
title = {Detailed Derivation of The Backpropagation Algorithm — arXiv:2611.02152},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02152},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fa10ff8f537; sha256 c83b161f363c653d6fa53842f5998ca990c9061e514f2037515e98092f6fade2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02152. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Backpropagation is the standard method for computing the gradients that train neural networks, but it is usually presented in a compact vector form that skips the intermediate steps. This tutorial derives backpropagation step by step for a fully connected feedforward network with sigmoid activations and a squared-error loss. Using a running example with three layers, we first differentiate the error with respect to a single weight by following its path through the network with the chain rule. We then show how summing over all paths leads to the error terms $\delta$ and to the four general backpropagation equations in matrix form. Every term is annotated with its dimensions, so each equation can be checked for consistency. The derivation is then extended to $m$ training examples, where the weight gradients become a single matrix product and the bias term corresponds to broadcasting. It is also extended to mini-batch gradient descent, including why the gradient of a mini-batch estimates the full gradient. Batch and mini-batch training are both given as algorithms. Finally, each equation is linked to the corresponding line of a NumPy implementation trained on the AHDBase dataset of handwritten Arabic digits, and the complete code is included. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.02152 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:07.955Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).