A Block Minifloat Representation for Training Deep Neural Networks - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Sean Fox, SeyedRamin Rasoulinezhad, Julian Faraone, David Boland, Philip H. W. Leong. A Block Minifloat Representation for Training Deep Neural Networks. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. [doi]

The following publications are possibly variants of this publication:

Single-Batch CNN Training using Block Minifloats on FPGAsChuliang Guo, Binglei Lou, Xueyuan Liu, David Boland, Philip H. W. Leong. fpga 2023: 53 [doi]

BOOST: Block Minifloat-Based On-Device CNN Training Accelerator with Transfer LearningChuliang Guo, Binglei Lou, Xueyuan Liu, David Boland, Philip H. W. Leong, Cheng Zhuo. iccad 2023: 1-9 [doi]

runs on WebDSL