MIT 6.S094: Computer Vision

This is lecture 4 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 - Computer Vision and Convolutional Neural Networks
22:15 - Network Architectures for Image Classification
34:39 - Fully Convolutional Neural Networks
44:35 - Optical Flow
50:07 - SegFuse Dynamic Scene Segmentation Competition
INFO:
Slides: bit.ly/2HdjksA
Website: deeplearning.mit.edu
GitHub: github.com/lexfridman/mit-dee...
Playlist: goo.gl/SLCb1y
CONNECT:
- If you enjoyed this video, please subscribe to this channel.
- AI Podcast: lexfridman.com/ai/
- Show your support: / lexfridman
- LinkedIn: / lexfridman
- Twitter: / lexfridman
- Facebook: / lexfridman
- Instagram: / lexfridman
- Slack: deep-mit-slack.herokuapp.com
LINKS:
Playlist: goo.gl/SLCb1y
Lecture 1: Deep Learning - • MIT 6.S094: Deep Learning
Lecture 2: Self-Driving Cars - • MIT Self-Driving Cars ...
Lecture 3: Deep Reinforcement Learning - • MIT 6.S094: Deep Reinf...
Lecture 4: Computer Vision - • MIT 6.S094: Computer V...
Lecture 5: Deep Learning for Human Sensing - • MIT 6.S094: Deep Learn...
Guest talk: Sacha Arnoud, Waymo - • Sacha Arnoud, Director...
Guest talk: Emilio Frazolli, nuTonomy - • Emilio Frazzoli, CTO, ...
Guest talk: Sterling Anderson, Aurora - • Sterling Anderson, Co-...
2017:
Guest talk: Sertac Karaman, MIT - • Sertac Karaman (MIT) o...
Guest talk: Chris Gerdes, Stanford - • Chris Gerdes (Stanford...

[@lucaspk33.]

# Some timestamps:
- Computer Vision is Deep Learning: 00:53 - 01:57
- Images are numbers: 01:58 - 03:13
- Visual Cortex: 03:51 - 04:37
- Deep learning is hard: 04:38 - 06:42
- KNN: 10:44 - 11:32
- Learning is optimization of a function: 12:05 - 12:42
- CNN: 13:36 - 21:30
- SENet: 29:30 - 32:06
- Capsule Networks: 32:07 - 34:23
- Fully Convolutional Networks: 35:22 - 37:53
- SegNet: 39:50 - 40:15
- Dilated convolutions: 40:16 - 41:05
- Deeplap: 41:06 - 41:49
- Key Aspects of Segment: 41:50 - 42:50
- ResNet-DUC
- FlowNet: 44:26 - 48:47
- FlowNet 2.0: 48:49 - 50:06

Amazing, thanks!

[@fgfanta]

Thank you chap!

[@guyathfaiz4479]

This so cool. I thought he was only a martial arts guy which was cool enough but he is also an AI guy in MIT. I began boxing this year and I will do EE next year. Leg locks and computer vision baby.

[@GG-jn9fx]

Been planning to get back in school next year and finish my EE. Now I’m going to take up Muay Thai this year, thanks for the inspo!

[@Jake-wm4lk]

Why EE for computer vision? EE is not computer vision

[@osvaldorivera8438]

About to graduate as EE hope u went thru w it !!

[@RobinTeuwens]

Very happy to see you will be dedicating time to the capsule networks. They are intriguing! Looking forward to it.

[@RoxanaNoe]

These lectures are amazing.

[@bennyfranklin]

Loved this. Thanks Lex. And thanks for your chat with Annie Jacobsen. My favorite of all your uploads sir.

[@RobinTeuwens]

Hey Lex, are you going to be uploading the lectures on capsule networks?

[@fergusmarktus]

Big ups Lex. Didn’t know you are a computer scientist. I watched your interview with Vitalik

[@kargarisaac]

Hey Lex. Thank you for great lectures. are GAN and CapsNet available online?

[@maxxu8818]

Dear Lex, thanks so much for providing such good series of videos. For the capsule networks and GAN mentions at last of this lecture? Where could we find the them?

[@LushPleiades]

love this. thanks lex

[@example.com.]

Awesome video

[@thenewculture2359]

his suit is sickkk

[@tatigabru8746]

Thank you Lex, very clear and informative.
One thing: 3.59 "the structure of the visual cortex is in layers". The slide before, differences, topology: human brains have no "layers" -- a bit misleading

[@yt-sh]

layers
i.pinimg.com/originals/f8/02/2b/f8022b97b8f6635176e1bbf8a1aa6ecc.jpg
lh3.googleusercontent.com/proxy/QmSOiqXmBvx793JGUDYl1XGudm9KRrXj3LWylx1J5pW1E6m3CPqBvDFbq-bUp23f7xdvyN0JHdMK1d8Cgx7MLd14BhQtEjPErLQQtZZpmcJNeCOS

[@10splay]

so he reads off a prompter...

[@mohanpannirselvam4102]

be yourself man

[@fracasopina2121]

Be me, I am cooler.