MIT 6.S191 (2020): Convolutional Neural Networks

MIT Introduction to Deep Learning 6.S191: Lecture 3
Convolutional Neural Networks for Computer Vision
Lecturer: Alexander Amini
January 2020

Lecture Outline
0:00 - Introduction
3:04 - What computers "see"
8:06 - Learning visual features
12:36 - Feature extraction and convolution
19:12 - Convolution neural networks
24:03 - Non-linearity and pooling
28:30 - Code example
29:32 - Applications
32:53 - End-to-end self driving cars
35:55 - Summary

Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

[mueez.mp]

As a lecturer myself, I'm blown away by the quality of the slides.

[beltusnkwawir]

As a computer science graduate student, it's unbelievable how simple Alexander breaks down these concepts in such a way that I'm getting it from a fresh perspective

[vidyaverma]

This is probably the best explanation of CNN that I have been through yet, it cleared almost all of my queries.

[domotorferenc]

Congratulations! Very well organized lecture. High standard and easy to follow at the same time. I am a 68 years old mechanical engineer with average capabilities, but I enjoyed each minute watching and listening to your presentation. Well done! Thank you very much indeed.

[lexifelix]

I never really understood convolution, but now I finally do! Thanks for this awesome lecture.

[FilipCodes]

Wow, that explanation with the X in the matrix of 1 and -1, and how we look for the mini sub features and compose a bigger picture out of them was awesome.

[reenietanya]

Amazing Lecture! The best on CNN. The only lecture probably that I’ve seen that cleared as to why each operations are done and how they influence the outcome. Thanks a ton. Much needed.

[Cgodwinokolinta]

Menhhh! This is arguably the best video on convolutional neural networks!!!

[adityavats]

You cannot get a better lec for CNNs. Thank You MIT.

[gavinliu]

This lecture is so clear and powerful. I simply love it. Respect

[impressivenow]

Hello Alexander, your presentation is very clean. I've seen many videos on CNN, and your presentation is actually very "clever" in the sense that you precisely tell about what's problematic and the reason why we solve issues this or this way. Pedagogically I admire your work, congrats.

[arthurkalikiti]

By far one of the very best lectures of Computer vision.

[원형석-kf]

19:02 Feature Extraction
19:50 CNNs for classification

[uchennanwosu]

Excellent exposition! The illustration of filters has helped me better understand the application of weights to learning. Please can you explain more about activation functions and their role with an example.

[poojaroi]

Clear and concise video on CNN. No need check another one on this topic. I am a student and performing plant disease detection and this would be very useful. Thanks !!

[tejaskhanna]

CNNs always intimidated me! This video made it really clear. 😀😀

[amc]

I know I will watch this several times over.

[akshayjaryal]

Simplistic way to teach with awesome presentation contents. Thank you for your hardwork. Happy Coding !!

[qusayhamad]

Awesome content and so clear explanation. Thank you very much for sharing these lectures with us.

[mrworf]

Best lecture on cNN that I have seen. Thanks mate!