all AI news
Mechanistic Design and Scaling of Hybrid Architectures
March 27, 2024, 4:42 a.m. | Michael Poli, Armin W Thomas, Eric Nguyen, Pragaash Ponnusamy, Bj\"orn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christoph
cs.LG updates on arXiv.org arxiv.org
Abstract: The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this process by grounding it in an end-to-end mechanistic architecture design (MAD) pipeline, encompassing small-scale capability unit tests predictive of scaling laws. Through a suite of synthetic token manipulation tasks such as compression and recall, designed to probe capabilities, we …
abstract architecture architectures arxiv compute costs cs.lg deep learning design development evaluation hybrid pipeline process prototyping scale scaling set space training type vast
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Applied Scientist
@ Microsoft | Redmond, Washington, United States
Data Analyst / Action Officer
@ OASYS, INC. | OASYS, INC., Pratt Avenue Northwest, Huntsville, AL, United States