Why 'Weird' Neurons Matter: Mixed Selectivity in Cortex Through the Lens of Cover's Theorem
burny_tech · x · 2026-10-02
Neuro blogger neurosock explains a paper on mixed selectivity across cortex (visual to PFC), linking it to Cover's theorem and arguing existing explainers fall short.
- Core claim: mixed selectivity is ubiquitous, and 'weird' neurons with nonlinear mixed coding play a key theoretical role.
- The Cover's theorem angle: nonlinear mixing in high dimensions makes linearly non-separable problems separable.
- The author shares a toy model and notes to illustrate the idea.
More from Research
- Audit: 23% of "wrong" cache hits in a semantic caching benchmark were identical prompts — Reasonable_Royal_621 · 2026-10-02
- Amazon Research Awards Fall 2026 opens with 9 research tracks, deadline Nov 4 — DocXavi · 2026-10-02
- Meta research: Knowledge distillation cuts training data memorization by over 50% vs fine-tuning — lasha_nlp · 2026-10-02
- Hugging Face publishes the ultimate guide to multi-harness RL — Saboo_Shubham_ · 2026-10-02
- From Transformers to MoE: The Research Papers Behind Every Major AI Concept — goyalshaliniuk · 2026-10-02
- MoE Paper Explained: Sparsely-Gated Experts Boost Model Capacity Over 1000x — goyalshaliniuk · 2026-10-02