Another paper on bio-plausible learning rules! Together with Ariane and the team, we confirm that local self-supervised learning can learn hidden hierarchical structures of synthetic datasets. On the same datasets, we also clarify the limitation of Direct Feedback Alignment.

GerstnerLab@gerstnerlab.bsky.social · last mo.

How can the brain learn the hidden hierarchical structure from high dimensional data? In our latest work, we use synthetic datasets to analyze two classes of bio-plausible learning rules: variants of Direct Feedback Alignment, and local self-supervised learning. We find only the latter succeeds.

Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve: 1. theoretical equivalence to BP in a controlled setup 2. new SOTA for local learning across image datasets 3. same performance as BP on multiple datasets