Binarized neural networks converge toward algorithmic simplicity: empirical support for the learning-as-compression hypothesis.

Sakabe EY, Abrahão FS, Simões A, Colombini E, Costa P, Gudwin R, Zenil H

Open source

DOI
10.3389/fncom.2026.1791546
Published
2026
Container
Frontiers in computational neuroscience
Publisher
Not recorded
Open access
yes

Credibility signals

limited evidence Score 45/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.3389/fncom.2026.1791546,
  title = {Binarized neural networks converge toward algorithmic simplicity: empirical support for the learning-as-compression hypothesis.},
  author = {Sakabe EY and Abrahão FS and Simões A and Colombini E and Costa P and Gudwin R and Zenil H},
  year = {2026},
  journal = {Frontiers in computational neuroscience},
  doi = {10.3389/fncom.2026.1791546},
  url = {https://doi.org/10.3389/fncom.2026.1791546}
}

RIS

TY  - JOUR
TI  - Binarized neural networks converge toward algorithmic simplicity: empirical support for the learning-as-compression hypothesis.
AU  - Sakabe EY
AU  - Abrahão FS
AU  - Simões A
AU  - Colombini E
AU  - Costa P
AU  - Gudwin R
AU  - Zenil H
PY  - 2026
JO  - Frontiers in computational neuroscience
DO  - 10.3389/fncom.2026.1791546
UR  - https://doi.org/10.3389/fncom.2026.1791546
ER  - 

APA

EY, S., FS, A., A, S., E, C., P, C., R, G., & H, Z. (2026). Binarized neural networks converge toward algorithmic simplicity: empirical support for the learning-as-compression hypothesis.. Frontiers in computational neuroscience. https://doi.org/10.3389/fncom.2026.1791546

Source records