Affiliation:
1. Leiden University, Leiden, South Holland, The Netherlands
2. University of Amsterdam, Amsterdam, North Holland, The Netherlands
Abstract
Convolutional Neural Networks (CNNs) are biologically inspired computational models that are at the heart of many modern computer vision and natural language processing applications. Some of the CNN-based applications are executed on mobile and embedded devices. Execution of CNNs on such devices places numerous demands on the CNNs, such as high accuracy, high throughput, low memory cost, and low energy consumption. These requirements are very difficult to satisfy at the same time, so CNN execution at the edge typically involves trade-offs (e.g., high CNN throughput is achieved at the cost of decreased CNN accuracy). In existing methodologies, such trade-offs are either chosen once and remain unchanged during a CNN-based application execution, or are adapted to the properties of the CNN input data. However, the application needs can also be significantly affected by the changes in the application environment, such as a change of the battery level in the edge device. Thus, CNN-based applications need a mechanism that allows to dynamically adapt their characteristics to the changes in the application environment at run-time. Therefore, in this article, we propose a scenario-based run-time switching (SBRS) methodology, that implements such a mechanism.
Funder
European Union’s Horizon 2020 Research and Innovation program
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Software
Reference44 articles.
1. Machine Learning-Based Image Classification for Wireless Camera Sensor Networks
2. Brandon Reagen Udit Gupta Robert Adolf Michael M. Mitzenmacher Alexander M. Rush Gu-Yeon Wei and David Brooks.2018. Weightless: Lossy weight encoding for deep neural network compression. In Proceedings of the 35th International Conference on Machine Learning .
3. Chi-Hung Hsu Shu-Huan Chang Da-Cheng Juan Jia-Yu Pan Yu-Ting Chen Wei Wei and Shih-Chieh Chang.2018. MONAS: Multi-objective neural architecture search using reinforcement learning. arXiv:1806.10332v2. Retrieved from https://arxiv.org/abs/1806.10332.
4. Keras;Chollet François;https://keras.io,2015
5. Searching toward pareto-optimal device-aware neural architectures
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. ARM-CO-UP: ARM COoperative Utilization of Processors;ACM Transactions on Design Automation of Electronic Systems;2024-09-04
2. ZIP-CNN: Design Space Exploration for CNN Implementation within a MCU;ACM Transactions on Embedded Computing Systems;2024-09-04
3. PELSI: Power-Efficient Layer-Switched Inference;2023 IEEE 29th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA);2023-08-30
4. Automated Exploration and Implementation of Distributed CNN Inference at the Edge;IEEE Internet of Things Journal;2023-04-01
5. Hierarchical Design Space Exploration for Distributed CNN Inference at the Edge;Communications in Computer and Information Science;2023