Lex Fridman
This is lecture 1 of course 6.S094: Deep Learning for Self-Driving Cars (2018 version). This class is free and open to everyone. It is an introduction to the practice of deep learning through the applied theme of building a self-driving car.
OUTLINE:
0:00 – Introduction
8:14 – Self-Driving Cars
14:20 – Deep Learning
INFO:
Slides: http://bit.ly/2HlyFHI
Website: https://deeplearning.mit.edu
GitHub: https://github.com/lexfridman/mit-deep-learning
Playlist: https://goo.gl/SLCb1y
CONNECT:
– If you enjoyed this video, please subscribe to this channel.
– AI Podcast: https://lexfridman.com/ai/
– LinkedIn: https://www.linkedin.com/in/lexfridman
– Twitter: https://twitter.com/lexfridman
– Facebook: https://www.facebook.com/lexfridman
– Instagram: https://www.instagram.com/lexfridman
– Slack: https://deep-mit-slack.herokuapp.com
LINKS:
Playlist: https://goo.gl/SLCb1y
Lecture 1: Deep Learning – https://youtu.be/-6INDaLcuJY
Lecture 2: Self-Driving Cars – https://youtu.be/_OCjqIgxwHw
Lecture 3: Deep Reinforcement Learning – https://youtu.be/MQ6pP65o7OM
Lecture 4: Computer Vision – https://youtu.be/CLOAswsxudo
Lecture 5: Deep Learning for Human Sensing – https://youtu.be/Z2GfE8pLyxc
Guest talk: Sacha Arnoud, Waymo – https://youtu.be/LSX3qdy0dFg
Guest talk: Emilio Frazolli, nuTonomy – https://youtu.be/dWSbItd0HEA
Guest talk: Sterling Anderson, Aurora – https://youtu.be/HKBhP9JISF0
2017:
Guest talk: Sertac Karaman, MIT – https://youtu.be/0fLSf3NO0-s
Guest talk: Chris Gerdes, Stanford – https://youtu.be/LDprUza7yT4
Source
Tips: Play at 2x speed 🙂
Very insightful lecture. (y)
So happy to see a new lecture of Lex Fridman and MIT… So interesting what Machine Learning & Deep Learning can do. Thank you!!
Good introduction Lex
What is their neural network (the one referenced on 19:30) running on?
Excellent lecture to watch again — big improvement over 2017 version. Thanks, Lex!
Beautiful. Grateful for these resources.
Thank you for uploading the video! Great stuff!
As soon I've finished my A levels, I'm setting aside a few hours a day to follow this course. Thanks very much for sharing this Lex!
Great talk. Simple. Good graphics.
Great lesson Professor. Thank you for sharing. You look like a former marine soldier … lol
Thanks for this informative lectures..http://www.artificialbrain.xyz/deep-learning-self-driving-cars-2018-version-lecture-1/
Is the last lecture open to the public I’d like to attend please!
Thanks for sharing the video lecture,
I have a question, is any big difference compared to 2017 video lectures and course content?
I love You!
Is the picture for L1 and L2 penalty at 38:54 misplaced?
Very good overview lecture
now if only there were some pill that actually made humans more intelligent, comprehensive, and competent to drive their own cars……
So many generations and I have been born in this.
I feel lucky.
I Like this course
Thanks much for the amazing videos Lex! Just ordered the T-Shirt.
what does it mean "not zero centered"?
Cool! Thank you!
Thank you so much for sharing this. I got a problem to download slides. Are those dropbox links still working?
When will you upload the rest?
17:46 Your suggesting that week make imaginary "poles", How with this work with public international law and such?. Its kind of like having a cloud of rules around you ( made to work with A.I.) So your cars can do the same thing, but use your poles, and thought space mechanically and physiologically, leaving you dumber and weaker. More susceptible to disease (thought process) Have you seen the countries that all where masks's everywhere they go, (mentally struck by technologies A.I. and such, there on a unique pole system there.
trivail data the seems wrong to human beings, = international law, A.I. intellegence take the place of judgement. (training that works if what he says is true), Lex Fridman talks about the 80's(decades),then list hundreds years, thousands years, and million years. (before that he says "is" "There is " 3 times, he also says "is not" and humans "do not" , lex sums it all up by saying " to/two winters" this is A.I. salesmen training. Its kind of dangerous becuase you could discredit, and take all he has said with a single word or phrase, I like to take the whole thing, and use it properly. A.I. training will back up what a human can do and says. Whens its all intergrated, and put together like this it carries alot of influence, there are billions of neurons trained in these bodies.TGB
Taking notes, or grading this presentation will go best with a magic marker, is samples your attention spanTGB
Shouldn't the Pong results be attributed to DeepMind rather than to Karpathy?
Thanks for making these series of lectures available free, on youtube.
1.25x speed is perfect
Thank you for sharing. Great lectures. Very simple, good graphics.
Mark and Learn
Really super cool lecture, and would you please upload the lecture of deep learning for driver state sensing?
What are the pre-requisites for this course?
great video
Does anybody know where to find Oliver Cameron's talk about how to start a self-driving car start-up ? I can't seem to find it.
Thanks!
Lex, thanks for let it open to the public. Best regards from my country Colombia
There seem to be a assumtion that a self driving car is the only autonomous vehicle in traffic. Let’s look at that ”90 – 10” page of what a self driving car can handle. It assumes for that 10% that there are a lot of humans involved, but as more and more cars are autonomous, more and more situations like this can be avoided. Imagine instrad L’arc de triumph being surrounded by self driving cars, communicating in a network. These types of situations would be avoided.
My point is that the human element of a car becomes less and less important the more care are autonomous. Lex Friedman points out human flaws, like being annoyed in traffic. I disagree that this will be an issue, since a car can communicate with another car and come to a conclusion how to solve the particular problem without a human involved. Human flaws like road rage can be torally eliminated when you take humans out of the equation. Or rather, a car will not be a car as we know it much longer.
The link to Slide 1 lectures indicates error. Does anyone know where to get these?
Can you please share the lecture slides for this lecture and other subsequent lectures as well. The link mentioned here is broken too!
where to find code…
Great lecture! Get hands dirty and work on the project!
15 AI boys from the future hate your coding skills. 733t bots rule humans drool