A 1.42TOPS/W deep convolutional neural network recognition processor for intelligent IoE systems

Jaehyeong Sim, Jun Seok Park, Minhye Kim, Dongmyung Bae, Yeongjae Choi, Lee Sup Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

115 Scopus citations

Abstract

Transmitting massive amounts of image and audio data acquired by Internet-of-Everything (IoE) devices to data center servers for intelligent recognition processes is impractical for energy reasons, requiring in-situ processing of such data. However, algorithms accelerated by previous recognition processors [1, 2] are limited to specific applications, therefore, each IoE device may require an application-specific accelerator. On the other hand, deep convolutional neural networks (CNNs) [3] are a promising machine-learning approach, showing state-of-the-art recognition accuracy in a wide variety of applications, including both image and audio recognition. This makes CNNs a suitable candidate for a universal recognition platform for IoE devices, as described in Fig. 14.6.1. Due to the computational complexity and significant memory requirements of CNNs, a microcontroller unit (MCU) typically used for IoE devices is incapable of producing a meaningful recognition result in an energy-efficient way. Hence, the implementation of an energy-efficient CNN processor is desired to realize intelligent IoE systems.

Original languageEnglish
Title of host publication2016 IEEE International Solid-State Circuits Conference, ISSCC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages264-265
Number of pages2
ISBN (Electronic)9781467394666
DOIs
StatePublished - 23 Feb 2016
Event63rd IEEE International Solid-State Circuits Conference, ISSCC 2016 - San Francisco, United States
Duration: 31 Jan 20164 Feb 2016

Publication series

NameDigest of Technical Papers - IEEE International Solid-State Circuits Conference
Volume59
ISSN (Print)0193-6530

Conference

Conference63rd IEEE International Solid-State Circuits Conference, ISSCC 2016
Country/TerritoryUnited States
CitySan Francisco
Period31/01/164/02/16

Fingerprint

Dive into the research topics of 'A 1.42TOPS/W deep convolutional neural network recognition processor for intelligent IoE systems'. Together they form a unique fingerprint.

Cite this