A Formal Proof of the Expressiveness of Deep Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Automated Reasoning Year : 2019

A Formal Proof of the Expressiveness of Deep Learning


Deep learning has had a profound impact on computer science in recent years, with applications to image recognition, language processing, bioinformatics, and more. Recently , Cohen et al. provided theoretical evidence for the superiority of deep learning over shallow learning. We formalized their mathematical proof using Isabelle/HOL. The Isabelle development simplifies and generalizes the original proof, while working around the limitations of the HOL type system. To support the formalization, we developed reusable libraries of formalized mathematics, including results about the matrix rank, the Borel measure, and multivariate polynomials as well as a library for tensor analysis.
Fichier principal
Vignette du fichier
paper.pdf (219.41 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02296014 , version 1 (24-09-2019)



Alexander Bentkamp, Jasmin Blanchette, Dietrich Klakow. A Formal Proof of the Expressiveness of Deep Learning. Journal of Automated Reasoning, 2019, 63 (2), pp.347-368. ⟨10.1007/s10817-018-9481-5⟩. ⟨hal-02296014⟩
62 View
211 Download



Gmail Mastodon Facebook X LinkedIn More