BROWSE
Detail
Journal Article
딥 뉴럴 네트워크 지원을 위한 뉴로모픽 소프트웨어 플랫폼 기술 동향
- Issue Date
- 2018-08
- Citation
- 전자통신동향분석, v.33, no.4, pp.14-22
- ISSN
- 1225-6455
- Publisher
- 한국전자통신연구원 (ETRI)
- Language
- Korean
- Type
- Journal Article
- Abstract
- Deep neural networks (DNNs) are widely used in various domains such as speech and image recognition. DNN software frameworks such as Tensorflow and Caffe contributed to the popularity of DNN because of their easy programming environment. In addition, many companies are developing neuromorphic processing units (NPU) such as Tensor Processing Units (TPUs) and Graphical Processing Units (GPUs) to improve the performance of DNN processing. However, there is a large gap between NPUs and DNN software frameworks due to the lack of framework support for various NPUs. A bridge for the gap is a DNN software platform including DNN optimized compilers and DNN libraries. In this paper, we review the technical trends of DNN software platforms.
- KSP Keywords
- Deep neural network(DNN), Graphical Processing Units(GPUs), Large gap, Programming environment, Software Framework, Tensor processing, easy programming, image recognition, software platform
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
