This is lecture 3 of course 6.S094: Deep Learning for Self-Driving Cars taught in Winter 2017. This lecture introduces computer vision, convolutional neural networks, and end-to-end learning of the driving task.
INFO:
Slides: http://bit.ly/2HdXYvf
Website: https://deeplearning.mit.edu
GitHub: https://github.com/lexfridman/mit-deep-learning
Playlist: https://goo.gl/SLCb1y
Links to individual lecture videos for the course:
Lecture 1: Introduction to Deep Learning and Self-Driving Cars
Lecture 2: Deep Reinforcement Learning for Motion Planning
Lecture 3: Convolutional Neural Networks for End-to-End Learning of the Driving Task
Lecture 4: Recurrent Neural Networks for Steering through Time
Lecture 5: Deep Learning for Human-Centered Semi-Autonomous Vehicles
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
Video Rating: / 5
►FREE YOLO GIFT – http://augmentedstartups.info/yolofreegiftsp
►KERAS Course – https://www.udemy.com/machine-learning-fun-and-easy-using-python-and-keras/?couponCode=YOUTUBE_ML
Hey guys and welcome to another fun and easy machine tutorial on Convolutional Neural Networks.
What are Convolutional Neural Networks and why are they important?
Convolutional Neural Networks (ConvNets or CNNs) are a category of Neural Networks that have proven very effective in areas such as image recognition and classification. ConvNets have been successful in identifying faces, objects and traffic signs apart from powering vision in robots and self-driving cars.
A ConvNet is able to recognize scenes and the system is able to suggest relevant captions for example (“a girl playing tennis”) while this image shows an example of ConvNets being used for recognizing everyday objects, humans and animals. There are also ConvNets involved in playing games like StarCraft, Mario and Doom.
ConvNets, therefore, are an important tool for most deep learning practitioners today. However, understanding ConvNets and learning to use them for the first time can sometimes be a bit daunting. But don’t worry you are in good hands here at Arduino Startups. If you are new to neural networks in general, I would recommend you check out my lecture on Artificial Neural Networks and then return to this one.
————————————————————
Support us on Patreon
►AugmentedStartups.info/Patreon
Chat to us on Discord
►AugmentedStartups.info/discord
Interact with us on Facebook
►AugmentedStartups.info/Facebook
Check my latest work on Instagram
►AugmentedStartups.info/instagram
Learn Advanced Tutorials on Udemy
►AugmentedStartups.info/udemy
————————————————————
To learn more on Artificial Intelligence, Augmented Reality IoT, Deep Learning FPGAs, Arduinos, PCB Design and Image Processing then check out
http://augmentedstartups.info/home
Please Like and Subscribe for more videos 🙂
Video Rating: / 5
My final project at school is autonomous driving with CNN. I have a problem with softmax function. I should take 3 steering output (right, left, straight) at the end of the CNN however how should CNN calculate steering angle values. Right,letf,straight do not mean anything if i dont know how much steering value. My training set outputs (steering values) changing between -1 and 1.
Note: Softmax function do not accept float values. It just accept integer and booleen.
what major is this, is it electrical engineering or informatic engineering or electronic engineering
Carssss
cars again
For those who already have a background in CNNs, the video starts at 36:15
Lots of great info on the nature of the subject of ai/nn in general!
Absolute perfection. Thank you Lex for all lectures.
Your lectures are really grate
(Y)
This guy seems way more like an engineer than a com sci background. That's a compliment (and a poke at CS majors) 🙂
Horrible lectures with no real content from which one can benefit. Feels like a summary presentation for a set of journalists who don't want to get technical!
THANK YOU! Computer Scientists and more people will appreciate 🙂
A short question: when traning a cnn network with back propogation , how the parameters change when passing through the pooling layer?
compatible version of jupyter notebook for tensorflow
If I remember correctly, there is also a rich kid got killed in Tesla's autopilot mode while driving in China. So that's 2 fatalities per 3million miles
Thank you for the excellent lectures! They are fantastic! And are the guest talks available on youtube (can't find links on the course page) ?
Your lectures are nice and straight to the point/application. Thank you
Are there good examples that explain step by step Image Segmentation and Object Detection. Its easy to find examples of image classification.
How can a conv. neural network perform better at classification than humens, if humans label the images? or is the labeling done in a different way?
I really like your lectures! Thanks for posting them!!
We live in incredible times that these lectures are available online. This information is crucial for my work and I have no idea how I'd be able to educate myself if I didn't have access to these lectures. I really appreciate your work.
Useful ! Thank you
Another gorgeous video Sir! I love Starcraft and this was such a delight to watch. You keep me up all night with all this outstanding material 🙂
Please create a video on word embedding such as word2vec
Thank you sir Augmented Startups for teaching Convolutional Neural Networks.
Super…. finally I got it! Very good explanations.
Augmented startups, or arduino startups??????
I want to implement CNN in python… please help me….
best example….hats off
Is the Convolution layer a separate Neural Network? Why are we calling it a layer? How do we pick the values of the convolutional filter? if arbitrary – are they adjusted somehow? Is Backpropagation happening only on the fully connected layer which is a separate neural Network? I thought Backpropagation can only be done with one Input layer and one output layer.
Great explanation…
Sorry Whay You Didn't continue the example till the end !!??
Great Explanation. Very simple and easy to understand. However i think the matrx multiplication values are incorrect at 5:00. The 3rd last pair should be (0x1) .