Improving Inference Time of Deep Learning Model with Partial Skip of ReLU-fused Matrix Multiplication Operations
- Authors
- Kim, Sungkyun; Kim, Jaemin; Kim, Nahun; Kang, Mincheal; Seo, Jiwon
- Issue Date
- Apr-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- deep learning optimization; fully-connected layer; inference optimization; omitted computation
- Citation
- 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022, pp.1 - 4
- Indexed
- SCOPUS
- Journal Title
- 2022 International Conference on Electronics, Information, and Communication, ICEIC 2022
- Start Page
- 1
- End Page
- 4
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138782
- DOI
- 10.1109/ICEIC54506.2022.9748210
- ISSN
- 0000-0000
- Abstract
- Deep learning has been expanding its application, while large-scale models tend to perform well. However, as such a model inevitably requires a vast amount of resources and computations, lengthy inference time is a crucial, but essential, consequence that needs to be optimized for the efficient utilization of deep learning. To achieve the goal, we aim at fusing the Rectified Linear Unit and matrix multiplication in the inference process, which we may reduce the total amount of computation by predicting the sign bit of output value. We propose four methods of prediction and statistically choose an optimal method for reducing inference time with low accuracy loss. © 2022 IEEE.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138782)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.