noemielteto.bsky.social

SR @DeepMind πŸ‡¬πŸ‡§; PhD student @MPICybernetics πŸ‡©πŸ‡ͺ; AI-like human interested in human-like AI, made in πŸ‡­πŸ‡Ί&πŸ‡·πŸ‡΄

Articles & links

14/14 By linking data-driven hypothesis generation with hypothesis-driven experiment selection, ATLAS shows real potential to accelerate the discovery of interpretable insights in cognitive science and beyond. Read the full paper here: arxiv.org/abs/2606.12386

ATLAS: Active Theory Learning for Automated Science arxiv.org
AI Weekly's analysis β†’
  • ATLAS combines sparse neural networks with active learning to generate and test mechanistic hypotheses automatically.
  • The system achieved 5-10x better sample efficiency than random experimentation across all evaluation metrics.
  • Validation compared ATLAS-designed experiments against expert-designed ones from published cognitive science literature.
Read full analysis β†’
View on Bluesky Β· β™₯ 2 ↻ 2 ↩ 1 Β· 3 from the directory shared this Β· 9d ago

Recent commentary

First paper since joining Google DeepMind! We present 🌍ATLAS (Active Theory Learning for Automated Science), a pipeline that generates interpretable mechanistic models from data and optimizes experiments to test them. Thread below

View on Bluesky Β· β™₯ 36 ↻ 7 ↩ 1 Β· 9d ago

In noemielteto.bsky.social's orbit

Center = noemielteto.bsky.social. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.