A review of new science, in plain language

PNAS Nexus  ·  23 September 2026  ·  From issue 41

Deep learning without weight symmetry

A new learning rule trains networks well without needing matched two-way wiring between neurons.

Li Ji-An, Marcus K Benna.

Integrity screen: passed (3 checks) Checked 6 October 2026. Read the source

The plain-language reading of this paper is in the full issue, for subscribers.

Read the full issue

Get it free, every two days

Five papers free every issue, about 15 emails a month. No spam. Leave in one click.

Also in issue 41 15 papers
More from PNAS Nexus