首页> 外文会议>International Symposium on VLSI Design, Automation and Test >Bringing Powerful Machine-Learning Systems to Daily-Life Devices via Algorithm-Hardware Co-Design
【24h】

Bringing Powerful Machine-Learning Systems to Daily-Life Devices via Algorithm-Hardware Co-Design

机译:通过算法-硬件协同设计将强大的机器学习系统带入日常生活设备

获取原文

摘要

While the recent breakthroughs achieved by machine learning (ML) systems promise to dramatically transform the way we live and work by enhancing our ability to recognize, analyze, and classify the world around us, such a transformation has yet to be unleashed. This is because powerful ML algorithms come at a cost of prohibitive complexity and energy requirements, whereas most daily-life devices, such as drones, wearables, self-driving cars, and smartphones, have limited energy, computation and storage resources. Towards bringing powerful ML systems into our daily-life devices, the Efficient and Intelligent Computing (EIC) Lab at Rice University explores techniques to empower daily-life devices with intelligence. In this talk, 1 will share some promising techniques we recently developed and exciting projects that we are working on.
机译:虽然机器学习(ML)系统最近取得的突破有望通过增强我们对周围世界的识别,分析和分类的能力来极大地改变我们的生活和工作方式,但这种转变尚未实现。这是因为强大的ML算法以过高的复杂性和能源需求为代价,而大多数日常生活设备(例如,无人机,可穿戴设备,自动驾驶汽车和智能手机)的能源,计算和存储资源却有限。为了将功能强大的机器学习系统带入我们的日常生活设备中,莱斯大学的高效和智能计算(EIC)实验室探索了使日常生活中的设备具有智能的技术。在本次演讲中,1将分享我们最近开发的一些有前途的技术以及我们正在努力的令人兴奋的项目。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号