Biuron

Local learning rules that scale to deep networks

A. Sato · Neuro Group

arXiv:2604.02218

Backpropagation requires a global backward pass no cortex could run. We study local learning rules, updates computed from information available at each synapse, and ask how far they scale.

On standard benchmarks, our rules train deep networks to accuracy approaching backpropagation, while offering a path to hardware that learns online and cheaply.

This is a plain-language summary. The full manuscript and supplementary material are available on request.

Collaborate

Want to build on this?

We work with researchers and institutions extending our published work into the real world.