June 6, 2024, 4:43 a.m. | Arnav Kundu, Prateeth Nayak, Hywel Richards, Priyanka Padmanabhan, Devang Naik

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.02652v1 Announce Type: cross
Abstract: Always-on machine learning models require a very low memory and compute footprint. Their restricted parameter count limits the model's capacity to learn, and the effectiveness of the usual training algorithms to find the best parameters. Here we show that a small convolutional model can be better trained by first refactoring its computation into a larger redundant multi-branched architecture. Then, for inference, we algebraically re-parameterize the trained model into the single-branched form with fewer parameters for …

abstract algorithms arxiv capacity compute convolutional count cs.ai cs.lg detection eess.as learn low machine machine learning machine learning models memory micro parameters show small training type

Senior Data Engineer

@ Displate | Warsaw

Principal Architect

@ eSimplicity | Silver Spring, MD, US

Embedded Software Engineer

@ Carrier | CAN03: Carrier-Charlotte, NC 9701 Old Statesville Road, Charlotte, NC, 28269 USA

(USA) Software Engineer III

@ Roswell Park Comprehensive Cancer Center | (USA) CA SUNNYVALE Home Office SUNNYVALE III - 840 W CALIFORNIA

Experienced Manufacturing and Automation Engineer

@ Boeing | DEU - Munich, Germany

Software Engineering-Sr Engineer (Java 17, Python, Microservices, Spring Boot, REST)

@ FICO | Bengaluru, India