Kording Lab amplifies thread: objective functions as concise descriptions of what neural nets learn
KordingLab · x · 2026-11-06
Kording Lab retweets a research thread by JRudoler: neural nets have too many interacting parameters to describe in words, so the authors propose objective functions and regularizers as concise descriptions of "what models learn," and ask whether implicit regularization in deep learning can be studied empirically. A thread on an empirical approach to understanding neural networks.
More from Research
- Rohit Krishnan maps "AGI institutions" experiments: 11 strong matches, zero at national scale — soumitrashukla9 · 2026-11-06
- Anneal V1 Core released: CPU-native low-parameter state-space architecture under CC0 — True-Beach1906 · 2026-11-06
- AI audit of 138 economics papers finds 2,035 errors, 69% of papers affected — panickssery · 2026-11-06
- No retraining needed: an LLM agent fixes a TTS model by editing weights directly — N1kuson · 2026-11-06
- Stanford paper proposes differentially private watermarks for LLMs — ChengleiSi · 2026-11-06
- Stanford PhD JulieKallini on testing Chomsky: can LMs learn a language no human could? — ChrisGPotts · 2026-11-06