Deep Learning for Autonomous Vehicles

2017 IEEE 47th International Symposium on Multiple-Valued Logic (ISMVL) Pub Date : 2017-05-01 DOI:10.1109/ISMVL.2017.49

B. Kisačanin

引用次数: 23

Abstract

In this talk we discuss the latest developments in the art and science of autonomous driving. Deep Learning Networks have become indispensable in design and implementation of such systems. We will present the latest software and hardware tools for development and deployment of ever more computationally demanding DLNs used in self-driving cars. From DGX-1 supercomputer for training DLNs, to Drive PX 2, a scalable AI car computer platform for inference, and looking into the future, to the recently announced Xavier, an AI supercomputer on a chip for future autonomous vehicles, tools are now available for every part of a DLN lifecycle. We illustrate how the tools are being used already by showing some of the most recent results of Nvidia's own, end-to-end DLN for autonomous driving.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

自动驾驶汽车的深度学习

在这次演讲中，我们将讨论自动驾驶艺术和科学的最新发展。深度学习网络在此类系统的设计和实现中已经不可或缺。我们将展示最新的软件和硬件工具，用于开发和部署自动驾驶汽车中对计算要求更高的dln。从用于训练DLN的DGX-1超级计算机，到用于推理和展望未来的可扩展人工智能汽车计算机平台Drive PX 2，再到最近宣布的用于未来自动驾驶汽车的芯片上的人工智能超级计算机Xavier，工具现在可用于DLN生命周期的每个部分。我们通过展示英伟达自己的端到端自动驾驶DLN的一些最新成果来说明这些工具的使用情况。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2017 IEEE 47th International Symposium on Multiple-Valued Logic (ISMVL)

自引率

0.00%

发文量

期刊最新文献

Extending Ideal Paraconsistent Four-Valued Logic Extensions to the Reversible Hardware Description Language SyReC A Random Forest Using a Multi-valued Decision Diagram on an FPGA Skipping Embedding in the Design of Reversible Circuits A Novel Ternary Multiplier Based on Ternary CMOS Compact Model