权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

CSR: Small: Evolution of Computer Vision for Low Power Devices, Breaking its Power Wall and Computational Complexity

CSR：小：低功耗设备计算机视觉的发展，打破其功耗墙和计算复杂性

基本信息

批准号：
1718538
负责人：
Avesta Sasan
金额：
$ 49.98万
依托单位：
George Mason University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-10-01 至 2021-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1718538&HistoricalAwards=false
关键词：
CSR Small Evolution Computer Vision

项目摘要

The accuracy of computer vision for object recognition and classification has surpassed human capabilities. Adoption of brain-inspired Convolutional Neural Network (CNN) models and the ability to train and execute these complex networks by modern graphical processing units (GPUs) are the backbone of this progress. However, in terms of computational requirement, memory usage, and power consumption, the CNN solutions are extremely demanding. Meanwhile, many interesting applications of computer vision - such as small robotics, a wide range of Cyber-Physical Systems, and many smart devices on the Internet of Things - are resource constrained. This project aims to substantially lower the computational complexity, the average-case classification power and the latency of CNN-based vision, enabling its deployment to a much wider range of platforms. From a societal viewpoint, this study enhances the research, education, and diversity at George Mason University (GMU) by involving graduate, undergraduate, minority and female students, and enriches several courses that are offered at GMU.The goals of this research project are as follows: (1) Reformulating the CNN-based learning model into an Iterative Convolutional Neural Network (ICNN) learning model that allows early classification and permits early termination via various thresholding mechanisms and developing a framework to use the contextual knowledge that could be extracted from earlier iterations to guide and reduce the computation of future iterations. (2) Developing an approximate ICNN coprocessor that supports approximation in memory and logic by exploring new approximation opportunities created by ICNN, and enhancing the ICNN to adjust and learn the approximate hardware behavior in addition to its intended functionality.

计算机视觉对物体识别和分类的准确性已经超过了人类的能力。采用受大脑启发的卷积神经网络（CNN）模型以及通过现代图形处理单元（GPU）训练和执行这些复杂网络的能力是这一进展的支柱。然而，在计算要求、内存使用和功耗方面，CNN解决方案的要求非常高。与此同时，计算机视觉的许多有趣应用-例如小型机器人，各种网络物理系统和物联网上的许多智能设备-都受到资源限制。该项目旨在大幅降低基于CNN的视觉的计算复杂性，平均情况分类能力和延迟，使其能够部署到更广泛的平台。从社会的角度来看，这项研究通过涉及研究生，本科生，少数民族和女性学生，并丰富了GMU提供的几门课程，增强了乔治梅森大学（GMU）的研究，教育和多样性。本研究项目的目标如下：（1）将基于CNN的学习模型重构为迭代卷积神经网络（ICNN）学习模型，允许早期分类，并允许通过各种阈值机制提前终止，并开发一个框架，使用可以从早期迭代中提取的上下文知识来指导和减少未来迭代的计算。(2)开发近似ICNN协处理器，通过探索ICNN创建的新近似机会来支持内存和逻辑中的近似，并增强ICNN以调整和学习近似硬件行为以及其预期功能。

项目成果

期刊论文数量（9）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

ICNN: An iterative implementation of convolutional neural networks to enable energy and computational complexity aware dynamic approximation

DOI：
10.23919/date.2018.8342068
发表时间：
2018-03
期刊：
2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)
影响因子：
0
作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan
通讯作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan

Exploiting Energy-Accuracy Trade-off through Contextual Awareness in Multi-Stage Convolutional Neural Networks

DOI：
10.1109/isqed.2019.8697497
发表时间：
2019-03
期刊：
20th International Symposium on Quality Electronic Design (ISQED)
影响因子：
0
作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan
通讯作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan

Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

DOI：
10.1109/isqed48828.2020.9136987
发表时间：
2020-01
期刊：
2020 21st International Symposium on Quality Electronic Design (ISQED)
影响因子：
0
作者：
F. Behnia;Ali Mirzaeian;M. Sabokrou;S. Manoj;T. Mohsenin;Khaled N. Khasawneh;Liang Zhao;H. Homayoun;Avesta Sasan
通讯作者：
F. Behnia;Ali Mirzaeian;M. Sabokrou;S. Manoj;T. Mohsenin;Khaled N. Khasawneh;Liang Zhao;H. Homayoun;Avesta Sasan

ICNN: The Iterative Convolutional Neural Network

DOI：
10.1145/3355553
发表时间：
2020-01-01
期刊：
ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS
影响因子：
2
作者：
Neshatpour, Katayoun;Homayoun, Houman;Sasan, Avesta
通讯作者：
Sasan, Avesta

TCD-NPE: A Re-configurable and Efficient Neural Processing Engine, Powered by Novel Temporal-Carry-deferring MACs

DOI：
10.1109/reconfig48160.2019.8994751
发表时间：
2019-10
期刊：
2019 International Conference on ReConFigurable Computing and FPGAs (ReConFig)
影响因子：
0
作者：
Ali Mirzaeian;H. Homayoun;Avesta Sasan
通讯作者：
Ali Mirzaeian;H. Homayoun;Avesta Sasan