深度学习基础教程:
麻省理工学院博士后Lex Fridman视频公开课
MIT opened the 6.S094 program in January 2017, which is called Deep Learning for Self-Driving Cars.
A course on the practice of deep learning explored through the theme of building a self-driving car. Course page is http://selfdrivingcars.mit.edu. Besides lectures and guest talks, it included a deep reinforcement learning competition (DeepTraffic) and an end-to-end driving simulation (DeepTesla).
麻省理工学院于2017年1月开设了 6.S094 课程,名为《深度学习与自动驾驶汽车》的课程,旨在教学生们为自动驾驶搭建一个深度学习系统,授课者为 Lex Fridman。
本课程是通过建立自动驾驶汽车的应用主题,介绍深度学习及其实践。本课程是专为机器学习初学者而设计,但该领域先进的研究人员也可以在此课的实践及应用中受益。
这次《深度学习与自动驾驶汽车》课程,大部分课程是由 Lex Fridman负责讲授,当然少不了 Lex Fridman加入的一个非常了不起的团队的帮忙,其中四个才华横溢的助教包括:Benedikt Jenik、Willian Angell、Apence Dodd、Dan Brown.
Lex Fridman
Postdoctoral Associate, AgeLab
Massachusetts Institute of Technology77 Massachusetts Avenue, Room E40-215
Cambridge, MA 02139-4307
Phone: 617.324.1693
fridman@mit.edu
http://lexfridman.com
Lex Fridman is a Postdoctoral Associate at the MIT AgeLab. He received his BS, MS, and PhD from Drexel University where he worked on applications of machine learning and numerical optimization techniques in a number of fields including robotics, ad hoc wireless networks, active authentication, and activity recognition. Before joining MIT, Dr. Fridman worked as a visiting researcher at Google. His research interests include machine learning, decision fusion, and numerical optimization.
Lex Fridman(莱克斯·弗里德曼)是来自麻省理工学院AgeLab的博士后研究员。他在德雷克塞尔大学获得了他的学士学位、硕士学位以及博士学位,他在那里从事机器学习和数值优化技术的应用,涉及机器人技术、无线网络、主动认证和活动识别等领域。在加入MIT之前,Fridman博士是谷歌的客座研究员。他的研究兴趣包括机器学习、决策融合和数值优化。
Administrative
·Website: cars.mit.deu
·Contace Email: deepcars@mit.edu
·Required:
·Create an account on the webisite
·Follow the tutorial for each of the 2 projects
·Recommendde:
·Ask questions
·Win competition
·Benedikt Jenik
Graduate student in Software Engineering at University of Augsburg, LMU Munich and TU Munich.
Currently doing deep learning research at MIT.
·William Angell (wha)
I'm currently working as an embedded systems/computer vision engineer at the MIT AgeLab.
I'm TAing 6.S094: Deep Learning for Self-driving Cars in January 2017.
·Spencer Dodd
I'm a Software Engineer who is supporting research on driver behavior and vehicle interaction at the MIT Agelab. Currently, I am working on RIDER (an in-vehicle data collection device) and its integration with the Agelab's driving simulator
·Dan Brown
I'm a researcher at the MIT Agelab where our primary focus is automotive safety using semi-autonomous driving features, HMI distractions, data collection and analysis. I have experience building and integrating intelligent systems into Tesla, Ford, GM, Volvo, Toyota, Jaguar Land Rover, and Mercedes vehicles. I recently was a teaching assistant for the MIT IAP course 6.S094 Deep Learing for Self-Driving Cars.
MIT深度学习与自动驾驶汽车公开课·第一讲【中文字幕】
·Lecture 1: Introduction to Deep Learning and Self-Driving Cars
课程(一):导论:深度学习与自动驾驶汽车
·Lecture 1 Part 1: 《深度学习与自动驾驶汽车》第一讲(一)
·Lecture 1 Part 2: 《深度学习与自动驾驶汽车》第一讲(二)
·Lecture 1 Part 3: 《深度学习与自动驾驶汽车》第一讲(三)
MIT深度学习与自动驾驶汽车-第一讲.pdf
MIT深度学习与自动驾驶汽车公开课·第二讲【中文字幕】
·Lecture 2: Deep Reinforcement Learning for Motion Planning
课程(二):运动规划与深度强化学习
·Lecture 2 Part 1: 《深度学习与自动驾驶汽车》第二讲(一)
·Lecture 2 Part 2: 《深度学习与自动驾驶汽车》第二讲(二)
·Lecture 2 Part 3: 《深度学习与自动驾驶汽车》第二讲(三)
MIT深度学习与自动驾驶汽车-第二讲.pdf
MIT深度学习与自动驾驶汽车公开课·第三讲【中文字幕】
·Lecture 3: Convolutional Neural Networks for End-to-End Learning of the Driving Task
课程(三):卷积神经网络与驾驶任务的端到端学习
·Lecture 3 Part 1: 《深度学习与自动驾驶汽车》第三讲(一)
·Lecture 3 Part 2: 《深度学习与自动驾驶汽车》第三讲(二)
·Lecture 3 Part 3: 《深度学习与自动驾驶汽车》第三讲(三)
MIT深度学习与自动驾驶汽车-第三讲.pdf
MIT深度学习与自动驾驶汽车公开课·第四讲【中文字幕】
·Lecture 4: Recurrent Neural Networks for Steering through Time
课程(四):递归神经网络与汽车转向
·Lecture 4 Part 1: 《深度学习与自动驾驶汽车》第四讲(一)
·Lecture 4 Part 2: 《深度学习与自动驾驶汽车》第四讲(二)
·Lecture 4 Part 3: 《深度学习与自动驾驶汽车》第四讲(三)
MIT深度学习与自动驾驶汽车-第四讲.pdf
MIT深度学习与自动驾驶汽车公开课·第五讲【中文字幕】
·Lecture 5: Deep Learning for Human-Centered Semi-Autonomous Vehicles
课程(五):深度学习与以人为中心的半自动汽车
·Lecture 5 Part 1: 《深度学习与自动驾驶汽车》第五讲(一)
·Lecture 5 Part 2: 《深度学习与自动驾驶汽车》第五讲(二)
MIT深度学习与自动驾驶汽车-第五讲.pdf
更新完毕·持续关注
后续精华视频·放送不间断