all AI news
Discovering modular solutions that generalize compositionally
March 26, 2024, 4:44 a.m. | Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wo{\l}czyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, Jo\~ao Sacramento, Angelika Steg
cs.LG updates on arXiv.org arxiv.org
Abstract: Many complex tasks can be decomposed into simpler, independent parts. Discovering such underlying compositional structure has the potential to enable compositional generalization. Despite progress, our most powerful systems struggle to compose flexibly. It therefore seems natural to make models more modular to help capture the compositional nature of many tasks. However, it is unclear under which circumstances modular systems can discover hidden compositional structure. To shed light on this question, we study a teacher-student setting …
abstract arxiv cs.lg cs.ne independent modular natural nature progress solutions struggle systems tasks type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Business Intelligence Architect - Specialist
@ Eastman | Hyderabad, IN, 500 008