Metraipolis › archive › dc_88b9de755d03
Understanding Deep Learning via Entropy Space Theory — arXiv:2608.29279
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29279
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:44:12.515Z
- SHA-256 of the archived text
b3db638038ac7576962ce0bb7982583a0f4eef4244bdd6d0c63034bcb3e62f93- Stable URL of this page
https://metraipolis.com/documento/dc_88b9de755d03
How to cite
Understanding Deep Learning via Entropy Space Theory — arXiv:2608.29279 — arXiv (en), https://arxiv.org/abs/2608.29279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88b9de755d03 (Metraipolis archive dc_88b9de755d03, sha256 b3db638038ac7576962ce0bb7982583a0f4eef4244bdd6d0c63034bcb3e62f93)
BibTeX
@misc{dc88b9de755d03,
title = {Understanding Deep Learning via Entropy Space Theory — arXiv:2608.29279},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29279},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88b9de755d03; sha256 b3db638038ac7576962ce0bb7982583a0f4eef4244bdd6d0c63034bcb3e62f93},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning is often criticized for its theoretical research lagging behind practice. To make deep learning easier to understand, the entropy space theory is first introduced here. The entropy space can cover all the possibilities of any deep learning model by topological structure. It is independent of network parameters. Through the designed fundamental operations and norm, entropy space is proven to be a normed space within the formal axiomatic framework. Based on the theory, a unified coordinate system is proposed. It can coordinatize every state of a model and rank them by compression of the maximal value of information entropy. The theory offers a novel priori framework for mathematical fundamentals of deep learning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29279 — 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 2026-10-17T07:28:26.534Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).