Self Driving Cars [S1E2: ALVINN]

TWITTER: @welchlabs

Welch Labs on backpropogation

Great 3B1B Video on backpropogation

FURTHER READING

VIDEO REFERENCES

MUSIC

SPECIAL THANKS TO
Tony Fast
Krish Ravindranath
Karthik Naga
Dean Pomerleau

- And -
Sid Sarasvati
Ross Hanson
Yana Chernobilsky
Vin Soma
Antoine Pintout
Jaewon Jung
Raphael J Vasquez
AJ Englehardt
Nate Fuller

[dpomerleau]

Stephen - I can't thank you enough for so clearly describing and demonstrating ALVINN. You've articulated the ideas behind it much better than I ever did! It is great to see that the early history of self-driving cars based on artificial neural networks captured for posterity.

[blackburnr]

I’ve always love Welch lab videos. My favorite is the complex number series. This series in my opinion is very well produced and definitely deserve more attention. You pulled a smart one by leaving us with more questions than answers. Hopefully all will be answered with the end of the series😁. Love your work man. Keep it up. 👍

[abhalla]

I don't think I've ever felt more eager for a next episode on YouTube than with this series.

[jean-gabrielmercier]

Most underrated YouTube channel, some of the highest quality content out there. Thanks a lot!

[VulpeculaJoy]

Ok when this series is done I'm going to convert an RC car with a raspberry pi and a camera and program it to drive on its own around Campus.
I didn't start studying mechatronics engineering for nothing!

[antoniopaladini]

These videos have the wrong order of magnitude of views, Dean Pomerleau himself is here watching!
Incredible work!

[rbc]

No better videos! Please keep up the amazing work!!

[pebre]

You're a master at explaining complicated topics. Kudos and keep it up!

[damianwiecaw]

Your videos are awesome, this quality damnnn, someday you will grow big

[كيوبتلتقنيةالمعلومات-لك]

i was waiting for this episode ... keep going

[JorgeCrespoyMuchomas]

Hola puede hacer este video sobre alvinn subtitulado o doblado en español por favor es muy interesante lo de multiplicación de matrices y retropacion y sobre peso de la red neural

[Leisloth]

I love the style of your videos, keep the good work up!

[haythamsaleh]

Will there be other videos in this series?

[bzztbzztboy]

Why are all the math youtubers so hot :0

[chil.]

This is the first time I've seen an example where the weights are actually meaningful to the human eye. So often when introducing neuro-nets, people will talk about what the weights could mean theoretically. Then when you actually see an example, the weights look completely meaningless to humans.

[speedseeder]

so this video is only a teaser for an other one?

[Huntracony]

6:41 I like how you can actually see the overfitting in the four weight pictures. The pixels above the skyline are not relevant to the actual driving, yet they have very strong weights, even stronger than the road pixels. The top pixels tell the AI where it is on the track by looking at the buildings and trees and decides to steer mostly based on that rather than the track.
I know that this problem would be fixed by a lot more training data, I just like how you can see it so clearly. And it certainly still shows that it has some understanding of the road, so it's good enough as a proof of concept.

[wladimirklein]

The major issue with ALVINN is that it can not properly handle the vehicle´s body motion, like pitching and rolling. These motions (among another plethora of issues with learned approaches) basically "smear" your input features in the weight map that you have shown. And once these "smearings" get too large the system can not derive useful steering angles any more. If you want to have a system that can handle this better you need something to estimate at least the vehicle pitch angle. This could be solved with either structure from motion or if you apply some modeling about the shape and appearance of the lane markings. If you see two lane markers on the left and the right side you can actually make a pretty goo estimate of the vehicle pitch, if you assume that the left and right marker are parallel. So this basic problem needs to be solved.... And we even did not start to talk about "mean" issues from the chaotic and "hostile" environment that the car is driving in ;-)

[pw]

The biggest problem with supervised learning for self-driving is the handling of exceptional situations. What was not part of the training data, is not part of the learned behaviour and may get mishandled. Think: New signage, animals or humans suddenly crossing the road, etc.
A combination with Reinforcement Learning is much more promising.

[BudskiiHD]

Just backed you on patreon, great channel