PNAS paper shows biological synapses can self-assemble learning rules akin to gradient descent
xuanalogue · x · 2026-10-18
In PNAS, Liu Ziyin, Tomaso Poggio and colleagues introduce Self-Assembling Learning (SAL) and the Self-Assembling Motif (SAM). Under heterosynaptic plasticity rules, SAMs emerge from initially random connectivity, and hierarchically composed SAM networks self-organize into dynamics that provably approximate generalized stochastic gradient descent, matching backpropagation-level performance. The upshot: biological learning need not be prescribed but can emerge from local rules to a far greater extent than previously thought — both the network and the learning rule itself can be learned.
More from Research
- Work in progress: geometric structure of GPG projections as Markov chain coarsening — michaelchchoi · 2026-10-18
- Backprop-free pretraining gets 2.3x speedup as Noise method crushes Dust record on 8 GPUs — inductionheads · 2026-10-18
- q3dviewer: open-source Qt+OpenGL tool for painter-like point cloud editing — 4310sy · 2026-10-18
- Smarter Every Day's Destin to defend PhD dissertation on impact fusion — CatAstro_Piyush · 2026-10-18
- Brain implants are restoring speech to people with ALS, Science reports — EricMTrautmann · 2026-10-18
- Formal Verification of LLM-Generated Code: Slides from FATTW 2026 Talk — CatAstro_Piyush · 2026-10-18