MIT 6.S191: Convolutional Neural Networks

MIT Introduction to Deep Learning 6.S191: Lecture 3
Convolutional Neural Networks for Computer Vision
Lecturer: Alexander Amini
* New 2024 Edition *

Lecture Outline
0:00​ - Introduction
2:45​ - Amazing applications of vision
4:56 - What computers "see"
13:09- Learning visual features
18:53​ - Feature extraction and convolution
22:12 - The convolution operation
28:38​ - Convolution neural networks
37:10​ - Non-linearity and pooling
41:23 - End-to-end code example
43:21​ - Applications
46:14 - Object detection
57:10 - End-to-end self driving cars
1:06:15​ - 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!!

[johnpuopolo]

Great series! Thanks for making the concepts approachable. These lectures are at a perfect level for understanding key concepts and for having the vocabulary and foundation for understanding other available materials. I especially found Ava's overview of Transformers and how the Q, K, and V matrices relate an "a ha" moment! Thank you, all.

[husseinekeita]

Thank you for sharing quality content like this for free for several years

[mahmoudjafari-tkry]

Dear Amini.was good trech too especially navigation too

[bytegraftkids]

I don't even need to be in MIT to learn from them! Outstanding and clear delivery of difficult concepts.Thank you.

[PerceptronsAI]

I wanted to extend my sincere thanks for the wonderful lecture you delivered on Deep Learning.

[vijaykumars]

Thank you, i have one doubt here, at 15:30 you said 10 k neurons in hidden layer for processing 10k parameters, so resultant would be 10k^2 parameters. My doubt is why we need 10 k neurons at any layer. we can decide the number of layers right?

[aiwroy]

While sliding window is good, YoLo outperforms Faster RCNN and is generally considered state of the art for object detection

[DreamBuilders-rqkm]

Thanks for sharing this knowledge. Be blessed

[htoorutube]

Software Lab 1 still not made available, when will that happen?

[fideslegoale]

Thank you for courses we are learning lot

[sudhirkothari]

fantastic ! thank you for the lectures

[karterel]

thank for sharing that course, that's so usefull !

[ghaithal-refai]

Thank you very much, it is a great lecture. I hope that you develop the lectures over the years as it seems to be the same contents. topics like pretrained models and knowledge transfer, YOLO might be good to be added to CNN

[ajayrathore]

The lecture is awesome but the quality of audio is very poor.

[meshkatuddinahammed]

I have a confusion about the Lab 2 Part 2 ( facial Detection with CNN). It has been claimed that in the CelebA dataset most faces are of light skinned females. But the model ultimately gives lower accuracy for this category of faces compared to other three categories. Why is that?

[suhaimiseliman]

EACH COLOR-
f RANGE.
ACTIVE CMOS SENSOR...
PHOTON>e BEAM
IF 3 LED CAN PRODUCE MULTICOLOR,
I 🤔 I CAN USE R, G & B BANDPASS FILTER TO GET THE SAME RESULT VIA SPECIAL PURPOSE DIGITAL OSCILLOSCOPE..😎😉

[noushadarakkal]

Thanks for this great lecture series.
However the audio is muffled at some points

[marlhex]

Hello Alex, please enlighten the peasants with a juicy time series episode? If you had been my teacher since I was a kid, I would be a different person today. Thank you for this, grateful today and in the future.

[albertmills]

It's weird that he uses Boston Dynamics robots in his first slides, since boston dynamics has gone on record saying they don't use AI.

[shahriarahmadfahim]

But the lab between Lecture 2 and 3 is still not published in the website?