LOL. I agree I think the same. However we seem to be running with it as something really cute n all because he made big advances in the AI field right, so, we see that and it's funny lol.
My heart just feels right when seeing superintelligient people like Andrew and Ian talk in such down to earth way. We need more people with such intelligience and humbleness to change our world.
Currently reading Deep Learning. Iinitially, the math sections were a little intimidating. Now, Im much more comfortable reading 'math' and have a much deeper understanding of previous machine learning knowledge I already had. Thank you Ian and Yoshua!!!
@@bobsmithy3103 There's a github repository which sports the pdf copy of the book. You can find it by just searching "mit deep learning". I'm not sure if that breaks any laws though :)
from this interview, these guys seem to have very admirable personas. I wouldn't know if the camera makes then extra vigilant. I admire their passion, to focus endlessly to resolve real-world problems. Why arn't political persons useful - Only loud mouth ego maniacs, with no self restraint want to be apart of politics.
The legendary interviewer realizing (at the beginning) and at the end of the interview that he was responsible for creating the GANgster! (or was it a hologram!)
I can bet 1000% Ian is an introvert that too deep introvert. His awkwardness is very clear. Man! they are contributing something in their life. Seeing them i feel whats the meaning of my life.
At 2:15, Andrew Ng mentions an old GPU paper that acknowledges Ian Goodfellow. But I cannot hear it. What old paper GPU paper acknowledges Ian Goodfellow?
GANs are great invention. I tried using CVAE but GANs give better results for high frequency components, but CVAE(conditional VAE) are easier to train, would had been great if GAN hyerpameter tuning would had been a bit easier,. just a wish list.
2 weeks ago when i saw "Ian Goodfellow" written in a article, i thought its misspelled and it is "I am Goodfellow" :p..................sorry for poor english
I wish I were smarter. I am about 100 pages into Ians Deep Learning Book, just up to section 5.7. Still a little tough for an old graduate like me. Apart from the maths, its a little frustrating that compute cycles for the majority if us is limited by GPUs, still taking hours to see if an typical CN algorithms are actually converging and performing. Deep Reinforcement Learning (e.g. DQN) still seems slow and fragile to iterate quickly to a robust solution.
You could use amazon web services and gain access to a fast gpu to test the CN algorithms. Check out course.fast.ai/lessons/aws.html to learn how to set it up. The cost is actually quite reasonable.
Math as we see it, is a way of imagining the universe. You either are there, or you are not. The whole challenge of Math education, is to get students to imagine the world through the lens of Math.
Thanks for the interview, Andrew. Hey fellow learners, is anyone interested in starting a weekly ML research paper reading and discussion group with me?
@@AndresMilioto incorrect, he wasn't trying to take credit for himself. He was trying to take credit for his research group, who spend countless hours trying different experiments. The research is like a puzzle with thousands of moving parts. In the end, some random guy comes in and connects the final piece and takes all the credit. How would that feel? Just imagine, you worked hard on some project but your manager takes all the credit, how would you feel then? Jurgen is a genius! He deserved the Turing. I have a mad respect for German scientists. American scientists not so much.
10:48 INDEED!!! Actually the societal, security, and policy aspect is one of the most fascinating aspects to me because this is often what gets most neglected when it could easily be argued that these topics are by far the most important. Let's not unwittingly create another "atomic bomb" without considering all the implications on society and human life just because we can. :'(
Ian seems like a good guy, and that's based solely on his last name
Mo Azim Ian is godfellow be like ian
LOL. I agree I think the same. However we seem to be running with it as something really cute n all because he made big advances in the AI field right, so, we see that and it's funny lol.
Mo Azim lololol
Not anymore since he joined apple. I just hope the company gives him a lot of respect.
rchavezj he probably got offered a 5m+ salary
the program running in Ian Goodfellow hasn't learned yet how to blink
Hahahahahha Yes.
One of the reasons he needs glasses. You need to blink to have healthy eyes.
Nope, this is a sign of a mind that can focus for a very long time
I can't believe such a good fellow invented such an adversarial algorithm.
Rumor has it that Ian used a GAN to create this video.
It would have been much smoother
I am disappointed that Andrew didn't say "concretely" more :P
LMAO
Niraj Pandkar conCREEtly
LOOOOOLOLOLOLOLLLL
"In this video..."
lolololol
My heart just feels right when seeing superintelligient people like Andrew and Ian talk in such down to earth way. We need more people with such intelligience and humbleness to change our world.
I echo this feeling of yours.
*humility
They're not superintelligient, just hard working.
Ian seems like a robot. In all the videos of him I watched, he talks as if he's reading a script. Zero error on speaking.
He's had a lot of training data
Not really.
EVA ZHAO czcams.com/video/Zd9kYgUjgSU/video.html
See this
oops caps...I DO IT TOO WHEN I WRITE OR MAKE FILM, EVERY WORD IS PERFECT BECAUSE 1) TRAINING AND 2) EDITING
He is an example of 100 % accuracy model
"Deep Learning" is beautifully written. A delight.
You can see how proud of him he is as a teacher! Amazing!
Eye blinking feature is still under development.
1:56 He did blink.
That was a fast reboot...
Even that blink looked artifical.
That wasn't a full blink.
@@JousefM 🤣
He never blinks.. incredible. Unless of course, he's a robot. Now let that sink in...
Actually this is a great predictor of focus that the person is capable of
Excellent interview. Down to earth, straight, and lot of information in this interview. Great work Andrew Ng with your contributions.
Thank you, Mr. Goodfellow.
What an inspiration!
Currently reading Deep Learning. Iinitially, the math sections were a little intimidating. Now, Im much more comfortable reading 'math' and have a much deeper understanding of previous machine learning knowledge I already had. Thank you Ian and Yoshua!!!
Did you have to catch up or learn completely from scratch?
And Aaron ;)
Is there a pdf version?
@@bobsmithy3103 There's a github repository which sports the pdf copy of the book. You can find it by just searching "mit deep learning". I'm not sure if that breaks any laws though :)
from this interview, these guys seem to have very admirable personas. I wouldn't know if the camera makes then extra vigilant. I admire their passion, to focus endlessly to resolve real-world problems. Why arn't political persons useful - Only loud mouth ego maniacs, with no self restraint want to be apart of politics.
Two great legends of machine learning 💗💗
Great legends are talking on great things.
The legendary interviewer realizing (at the beginning) and at the end of the interview that he was responsible for creating the GANgster! (or was it a hologram!)
I tried not to blink my eyes before Ian does...but I lost...because he never blinks his eyes! I guess that's genius's superpower.
Why do neurotypical minions like you have to observe these minor details?
This is awseome
I like your speech , you are great. (y)
Two amazing teachers !
I can bet 1000% Ian is an introvert that too deep introvert. His awkwardness is very clear. Man! they are contributing something in their life. Seeing them i feel whats the meaning of my life.
Andrew's voice be hitting diff🔥
it's funny how Andrew says: "oh, i didn't know that"
he always says that. Either that or 'I had forgotten that" or 'I forgot about that (one)" the brackets are optional.
goodfellow is not even blinking his eyes. seems like robot
Reminds me of Harold from Persons of Interest
Ian Goodfellow will make a great evil-genius villain in a science-fiction movie LOL
Hasnain Abbas Dilawar That is impossible. He is a goodfellow.
agree
agree with both of yous at the same time....
He disguise by his name
Ian Badfellow
Does anyone knows how to get script or subtitles of this interview? Since I really want to practice English with this video.
man....he never blinks it seems
Neurodivergent
Please upload 720p videos atleast...1080p would be better ... content is good...
It's just two people sitting still, which cares what the resolution is ahaha
I am going to even watch this video; in its entirety, but I they are not ever in the same frame together.
At 2:15, Andrew Ng mentions an old GPU paper that acknowledges Ian Goodfellow. But I cannot hear it. What old paper GPU paper acknowledges Ian Goodfellow?
GANs are great invention. I tried using CVAE but GANs give better results for high frequency components, but CVAE(conditional VAE) are easier to train, would had been great if GAN hyerpameter tuning would had been a bit easier,. just a wish list.
Where did you use GANs
He seems like a Good fellow.
Omg That guy doesn't blink
He looks so young
2 weeks ago when i saw "Ian Goodfellow" written in a article, i thought its misspelled and it is "I am Goodfellow" :p..................sorry for poor english
Andrew seem to like this shirt very much
Why the camera quality poor
LOOL he really does seems like a robot.
That's interesting watching
Mr. Ian seems to be a Goodfellow....
GANs are so similar to how biology competes and progresses. Genius
10:20 second blink
The bad boy of deep learning
Seems like a good fellow
I wish I were smarter.
I am about 100 pages into Ians Deep Learning Book, just up to section 5.7. Still a little tough for an old graduate like me. Apart from the maths, its a little frustrating that compute cycles for the majority if us is limited by GPUs, still taking hours to see if an typical CN algorithms are actually converging and performing. Deep Reinforcement Learning (e.g. DQN) still seems slow and fragile to iterate quickly to a robust solution.
Keep reading man. The brain is malleable. You will be smarter when you have finished reading. Don't skip math. Fight it. You will win eventually.
You could use amazon web services and gain access to a fast gpu to test the CN algorithms. Check out course.fast.ai/lessons/aws.html to learn how to set it up. The cost is actually quite reasonable.
fast.ai has provided some solution of GPUs like aws, gcloud also provide gpus equally free for some time, for some kind scale problem may it's enough.
no google cloud does not provide free GPU. GPUs are excluded from the $300 free trial
According to the sub, they are talking about games.
subtitles is where i'm going lol
Math as we see it, is a way of imagining the universe. You either are there, or you are not. The whole challenge of Math education, is to get students to imagine the world through the lens of Math.
wow
Genius play respect to genius.
1:55 there he blinks
Thanks for the interview, Andrew. Hey fellow learners, is anyone interested in starting a weekly ML research paper reading and discussion group with me?
Mark F I'm interested
@@anish2197 Hey, cool. Email me at markdfoti at gmail dot com
Hi I am interested
Cool
Andrew Ng is talking spanish
ian is my favorite hero. him owning schmidhuber was priceless
B Doom how did he own him?
ah, I see. I was not aware this occurred. Was this recorded or something like that?
which link?
@@AndresMilioto incorrect, he wasn't trying to take credit for himself. He was trying to take credit for his research group, who spend countless hours trying different experiments. The research is like a puzzle with thousands of moving parts. In the end, some random guy comes in and connects the final piece and takes all the credit. How would that feel?
Just imagine, you worked hard on some project but your manager takes all the credit, how would you feel then?
Jurgen is a genius! He deserved the Turing. I have a mad respect for German scientists. American scientists not so much.
Two bots talking to each other.
When one watches their mannerisms it's entirely possible
is this real or artificial?
Oh shit! Ian is a robot!
Lan was Andrew's student and now Andrew is interviewing him.
Did you mean *Ian*?
Great, then what happened?
he needs to work at Facebook meta platforms!
Thank's What is Guns? I have to see what that is.
It is GANs, short for Generative adversarial networks, invented by Ian
lol, you made me laugh :D. not dissrespecting we all are in a learning process.
Olle, GUNS is a great acronym for a new kind of neural net. Maybe it will be the next big thing. Now, if only we can figure out what it stands for.
All the dialogue in this video is computer generated
Ian looks like a lovely talking humanoid robot. lol
these two i hope are billionaires
They are not money minded and do if for passion.
he is not moving his eyes..!! almost like blind people i have seen in movies.
Does this guy actually not blink????????????
stop boxing him into certain patterns. we all are different in some manners. Not everyone has to follow some code.
10:48 INDEED!!! Actually the societal, security, and policy aspect is one of the most fascinating aspects to me because this is often what gets most neglected when it could easily be argued that these topics are by far the most important. Let's not unwittingly create another "atomic bomb" without considering all the implications on society and human life just because we can. :'(
I dont even think about russia
is youtube using ML for the title generation? it feels very robotic
If youtube did generate it, it would be more like "SHOKING PRANK ON AI ROBOTS: NG ANDREW CLASH IAN GOODFELLOW"
Stoneface GOD
Stabalizing GANs is easy. Just make a program that automaticly tweak paramters and it will work perfectly.
schmidhuber created 20 accounts and disliked this video
. Yeah, I am pansexual & got attracted to Ian
This doesn't undermine anything he says of course, but Ian looks a bit unhealthy here.
So disappointed in the number of views Ian's videos has. Like what is the rest of the world paying attention to??...