@ac-schneider.bsky.social
Excited to share our new @PNAS paper: We introduce “infomorphic” neurons that learn by maximizing individual, information-theoretic objectives. This general framework on interpretable neural learning is applicable across different learning paradigms. Read more: doi.org/10.1073/pnas... 1/2
A general framework for interpretable neural learning based on local information-theoretic goal functions | PNAS
Despite the impressive performance of biological and artificial networks, an intuitive
understanding of how their local learning dynamics contribut...
doi.org
March 17, 2025 at 9:48 AM
Excited to share our new @PNAS paper: We introduce “infomorphic” neurons that learn by maximizing individual, information-theoretic objectives. This general framework on interpretable neural learning is applicable across different learning paradigms. Read more: doi.org/10.1073/pnas... 1/2
Reposted
PNAS: A general framework for interpretable neural learning based on local information-theoretic goal functions
https://www.pnas.org/doi/abs/10.1073/pnas.2408125122?af=R
https://www.pnas.org/doi/abs/10.1073/pnas.2408125122?af=R
March 13, 2025 at 11:18 AM
PNAS: A general framework for interpretable neural learning based on local information-theoretic goal functions
https://www.pnas.org/doi/abs/10.1073/pnas.2408125122?af=R
https://www.pnas.org/doi/abs/10.1073/pnas.2408125122?af=R