May 27, 2024, 4:45 a.m. | Cansu Demirkiran, Guowei Yang, Darius Bunandar, Ajay Joshi

cs.LG updates on arXiv.org arxiv.org

arXiv:2311.17323v2 Announce Type: replace-cross
Abstract: Photonic computing is a compelling avenue for performing highly efficient matrix multiplication, a crucial operation in Deep Neural Networks (DNNs). While this method has shown great success in DNN inference, meeting the high precision demands of DNN training proves challenging due to the precision limitations imposed by costly data converters and the analog noise inherent in photonic hardware. This paper proposes Mirage, a photonic DNN training accelerator that overcomes the precision challenges in photonic hardware …

abstract accelerator arxiv computing cs.ai cs.ar cs.lg dnn inference limitations matrix matrix multiplication networks neural networks photonic computing precision replace success training type while

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