Lex Fridman
The talks at the Deep Learning School on September 24/25, 2016 were amazing. I clipped out individual talks from the full live streams and provided links to each below in case that’s useful for people who want to watch specific talks several times (like I do). Please check out the official website (http://www.bayareadlschool.org) and full live streams below.
Having read, watched, and presented deep learning material over the past few years, I have to say that this is one of the best collection of introductory deep learning talks I’ve yet encountered. Here are links to the individual talks and the full live streams for the two days:
1. Foundations of Deep Learning (Hugo Larochelle, Twitter) – https://youtu.be/zij_FTbJHsk
2. Deep Learning for Computer Vision (Andrej Karpathy, OpenAI) – https://youtu.be/u6aEYuemt0M
3. Deep Learning for Natural Language Processing (Richard Socher, Salesforce) – https://youtu.be/oGk1v1jQITw
4. TensorFlow Tutorial (Sherry Moore, Google Brain) – https://youtu.be/Ejec3ID_h0w
5. Foundations of Unsupervised Deep Learning (Ruslan Salakhutdinov, CMU) – https://youtu.be/rK6bchqeaN8
6. Nuts and Bolts of Applying Deep Learning (Andrew Ng) – https://youtu.be/F1ka6a13S9I
7. Deep Reinforcement Learning (John Schulman, OpenAI) – https://youtu.be/PtAIh9KSnjo
8. Theano Tutorial (Pascal Lamblin, MILA) – https://youtu.be/OU8I1oJ9HhI
9. Deep Learning for Speech Recognition (Adam Coates, Baidu) – https://youtu.be/g-sndkf7mCs
10. Torch Tutorial (Alex Wiltschko, Twitter) – https://youtu.be/L1sHcj3qDNc
11. Sequence to Sequence Deep Learning (Quoc Le, Google) – https://youtu.be/G5RY_SUJih4
12. Foundations and Challenges of Deep Learning (Yoshua Bengio) – https://youtu.be/11rsu_WwZTc
Full Day Live Streams:
Day 1: https://youtu.be/eyovmAtoUx0
Day 2: https://youtu.be/9dXiAecyJrY
Go to http://www.bayareadlschool.org for more information on the event, speaker bios, slides, etc. Huge thanks to the organizers (Shubho Sengupta et al) for making this event happen.
CONNECT:
– If you enjoyed this video, please subscribe to this channel.
– AI Podcast: https://lexfridman.com/ai/
– Show your support: https://www.patreon.com/lexfridman
– 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
Source
Why the white-board is "all-white"? DO these big organizers care for these basic details??
With all the intelligence expected from machines, what happened to the responsibility and common sense of the human brains?
Hereby I declare myself as the biggest fan of Ng. He has this amazing capability of simplifying the most complex equations. Hats off to you sir. !!
ANSWER TO ETHICS CAR CRASH DEBATE = If a crash is eminent to have a fatality and AI must make a decision to kill x or yz people. answer = AI hacks x and yz units and forces them to move. Should anti-AI trust software prevent AI from moving x or/& yz, it was x or/& yz 's persons conscious fault and decision. NOT AI's
Thanks for the great lecture 🙂
Andrew Ng is a corporate sell out.
Also, If you have to "code it" it is not AI so don't call it that!
Damn, I thought the title was "Nuts and Bots!"
incredible useful and so amazing,one of the best speech I ever heard…
We are all in debt to Andrew Ng
Very nice practical lecture. About his rule of thumb though, I don't think our doctors decide on cancer image in 1 second. Is he underpromising, over delivering?
AdHoc, not very impressed. I was hoping for a proof on say optimizing design, not some words of advise. Meh..
At the end of the talk about how to get better at machine learning. Andrew states we should read more papers (add more data), and work at it for longer periods of time (train the model longer). Literally the same stuff for the algorithm improvements….
Andrew, question — can you please tie your shoe lace?
If you are here for some advice on how to build a ML/DL career, start from here 1:10:25
TPU :Taste & Speech Processing Unit
https://youtu.be/eM9wu-s_QyI
TGBmulti
30:16 yo ng Andrew, what do you think about angles distortion alongations zoom. ? 35:49
think about a bird in the air with airplane above it. SID OID IMAGE OBJECT Distance IOD TGB OID
they might look the same size in appearance. This example puts physiology and pereception in the equation, with thinking, (nervous system) understanding. comprehenstion to be discovered. TGB
instead of thinking technology, think about a bird in the air, with a shine on it. What do you think about a hawk that looks gold in the air flying in circles, what is the energy what perception do we use from it?TGB, we are the most brilliant thing on the planet the best part of each animal so to speak.
Also for the google team, (the spell check guys or whatever your called)
Google, Zoom is created by OID regulation focus. SOCHASTIC distortion. would be away to describe being as boring as possible.
At the begening of the video, Ng Andrew, goes through a couple of steps to attempt to separate him from the lesson. He then Seperates your outgoing attention , theres lots of sound stuff going on , intent of forced listening to gain access to . calculating (setting the tone) what volume is, where action to volume is. multiple sub division. or a spliced wire to be put back together (figured accordingly)TGB He is using the bilingual trick here though, I mean what can you say/whats to say, if you have it, your made not to use it, its going to surface in some platform. Lets make it good Andrew (chineese (Asian)pie sign TGB) I'm gonna put it on a grilled cheese sandwhichTGB
But he knows its there, uses it uniformly in a specific place.
He is a shill.
He is telling the truth about whats happenning right at your face. He's a shill, he's mocking you. He's a deceiver! Don't trust him, believe in Christ only. He is the Truth.
Topnotch.
Ingenious, very comprehensive grasp of the subject
"Humans are pretty good at computer vision" @54:30
lol
HPC team == Data Engineering team ? https://youtu.be/F1ka6a13S9I?t=435
very great talk.
Great Teaching and Thanks for Professor Ng
does this guy have to pee?
If you want to learn or comment on this topic, I invite you to read this article: https://www.linkedin.com/pulse/artificial-intelligence-new-electricity-you-kidding-me-l-hijazi/?published=t
The great Andrew Ng.
Not to promote stereotypes but… Andrew Yang ? Is that you
Amazing talk, but what if the test set is unlabelled will it be still be useful to use some part if it as validation set?
the 1st person pops up to my mind is his name in terms of ML and AI and DL
Andrew Ng looks so much like Andrew Yang.
I didnt know andrew yang was this involved in AI
God damn, Andrew Yang's a math teacher too!??
that was a pretty good talk
Andrew Yang is copying Bernie Sanders 100% LOL
Machine learning looks promising. Still pretty narrow AI but it will be interesting to see if general machine learning is invented soon, maybe not in 2020 but who knows. Exponential progress!
He’s truly energetic! Campaigning during day time and teaching programming at nights. Respect!
Although I am a Bernie guy, I have much respect for Andrew nYang 😉
When you click thinking its a dope politician only to find out its a dope machine learning legend.
Andre Yang going brazy..MATH
Andrew Ng looks so much like Andrew Yang.
Soft voice, the ability to convey in simple terms to masses, openness. Awesome Guy
Thank you for the upload 🙂
I didn't understand at 27:23, if the training error is high then it's mean we are having high bias in training error. Please explain this point a little bit. Thanks
Soft voice, the ability to convey in simple terms to masses, openness. Awesome Guy
Andrew Ng is the best at teaching us machine learning , deep learning all the stuff. GURU
Andrew Ng is my ML sensei
HE has taught me so much on Machine Learning. We all owe him 🙂
HE has taught me so much on Machine Learning. We all owe him 🙂