can you please explain? I understand the dot product but not the joke. I dont see selfawareness at all, unless you come from 1950 and play against alpha zero.
That’s exactly the point. There is no self-awareness. He is making fun of the fact that whenever there is a big breakthrough in AI (e.g. AlphaGo beating the world champion in Go 0:25), mainstream media in general immediately jumps to the conclusion that a general artificial intelligence is near (and you are bound to find Skynet comments under respective news articles or videos). But at the core deep learning is basically just a bunch of dot products and activation functions. So, just basic mathematical operations. There is nothing that is inherently “intelligent” about that, let alone self-aware.
@@SebastianMantey there is nothing 'self-aware' about 2 atoms and yet they make up our brains. This is identical to the argument you just used. Self-awareness, is also independent of power or danger. Self-awareness, consciousness, sentience may not even exist.
1:25 Move 37 was not an invention of AlphaGo. The documentation says it was played by 1:10.000. Bcs the data based on 10.000 games from human amatures, the frequency was one of the human player out of 10.000 human players, which were the base data of AlphaGos learning pattern, which it could optimize but not surpass. That also explains the dead lumps in AlphaGos strategy.
The mentioned move 37 was played in game 2 of 5, which was streamed here: th-cam.com/video/l-GsfyVCBu0/w-d-xo.htmlh17m46s At the bottom right of the video at 1:17:46 you can see that black (AlphaGo) is playing the 37th stone. The reaction of the moderators is funny :)
Siraj, you've improved your skill of teaching a lot over the years! Now, you talk more slowly and your videos are much more comprehensive than before! Beautiful. Keep going! :D
I have a question on "The outputs of neural network are: 1)possibilities for each next move and 2)possibility of win." Does "possibilities for each next move" correspond to one-hot encoding for the next move?
Thank you! Somehow in every previous explanation I missed the fact that MCTS involved purely random playouts. As a Go player, it surprises me that purely random moves would be a good diagnostic for the goodness of a move. It makes sense that strong shape (for instance) would withstand a random barrage of stones better than weak shape. Perhaps the same goes for small territories vs. large areas, which could be why AG prefers quick territory over whole-board influence. Random playouts seem like they would be less effective in complicated fights, where there are several possibilities at the local scale, let alone the whole board, but am I correct that the layers of neural networks involve smaller portions of the board, and so it might be able to deduce the correct local sequence from fewer playouts than otherwise?
What I'm curious about AlphaGo, is if there's "hidden technology" on its making. That is, I know the source is closed, but a lot of its designs are available in papers. Would someone with enough resources be able to create his own version of AlphaZero without having to research new technology (i.e. just coding based on the papers)?
can you do a video about AI natural language understanding, with all the data we have in books and on the web an algorithm using that data should be able to learn to understand language, how far are we in that area what are the main issues?
Ymi_Yugy Hyperparameter tuning is only for supervised learning . Reinforcement learning is super dope , relying only on the algorithm and the training process to get better and better.
Hello Siraj ! Thank you for the video ! I am a newbie here and I wanna build my own AI for Go. Do you think a genetic neural network approach can suit this application ? :D
sir,thnx 4 instr,many ppl begin playing chess/go by remembering win/draw patterns(if u place stones in certain position,ur opponent have no other choice but follow u,thus u can control the result),there r many books about these "patterns"& tactics,r they real tesed by ai?
If human mind also has good capacity to traverse all possible state space(may be by tree search and others ) at the speed of computer processors/GPU, would it be that AI and human level would be the same on especially for the game like alphago?
Hey Siraj, great video thow, I would recommend you that you don't animate every element on your diagrams with transitions, (feels a bit power pointy), instead just show the whole diagram (e.j. a neural network) and only highlight the piece of the diagram you are talking about, the same with the code, place as much code (or pseudo code) as possible, and highlight the important part(sometimes not even the whole line) as you mention it, I think that would make your explanations more clear, and visuals less distracting, but for the love of A.I., the memes, don't change them, they are great.
I am a Master student of Machine Learning and Data Mining, I love your videos. I just have a small complaint that, it's sometimes hard to follow you when you're explaining really tough concepts. I know you have time constraints but it becomes nearly impossible to follow you in long explanations that you provide. If you could bring some pause between some really tough concepts, it will be little easy to follow you in better way.
I have the same question: this result is based on TPU according to my information. Why only mention GPU en CPU? TPU cost more! about 10.000 $ for a unit, maybe. Titan V cost about 3000$.
you should help promote Dataquest.io for everyone trying to get into A.I and data science its a great resource that truly allows anyone to get into the field.
right, but how does that make the number of Go positions larger than the number of atoms in the universe? You don't even know how many particles there are in the universe. At best, you can approximate the number of atoms in the observable universe and make your claim against that.
It's not known that the universe is infinite. In fact it is more likely believed to be finite, as we had a big bang and the universe expands from that moment, over a finite(but large) period of time
thank our AI god-masters -- may AlphaZero reign supreme -- that this video did not include tasteless royalty-free music to detract from the lesson lol what if humans create a religion out of AI :D. wait. actually it sounds plausible :(
If AI system has way better than human beings, how possibly we human being maintain ruler of AI? It's like ants create human beings. I'm deep learner but still has huge conspicuous thoughts on safety of AI finally when we get into AGI period.
The problem is that a superior intelligence has no reason to share its intelligence with apes. Why on earth would it combine itself with us. We'll be pets in the best case scenario. Which isn't bad, I could live as a cat. Minus the neutering but I'm afraid there's no way out of that once it starts to genetically engineer us to be cuter and less violent.
Hey, @Siraj! It seems to be a mistake at 3:23
Green and cyan colors must be replaced, I suppose?..
jup
yes, thanks for pointing that out my mistake
“The dot product operations became self-aware.” (1:34) 😂 Nice point of view to put the danger of artificial “intelligence” somewhat in perspective.
can you please explain? I understand the dot product but not the joke. I dont see selfawareness at all, unless you come from 1950 and play against alpha zero.
That’s exactly the point. There is no self-awareness. He is making fun of the fact that whenever there is a big breakthrough in AI (e.g. AlphaGo beating the world champion in Go 0:25), mainstream media in general immediately jumps to the conclusion that a general artificial intelligence is near (and you are bound to find Skynet comments under respective news articles or videos).
But at the core deep learning is basically just a bunch of dot products and activation functions. So, just basic mathematical operations. There is nothing that is inherently “intelligent” about that, let alone self-aware.
thx
haha thanks
@@SebastianMantey there is nothing 'self-aware' about 2 atoms and yet they make up our brains. This is identical to the argument you just used.
Self-awareness, is also independent of power or danger. Self-awareness, consciousness, sentience may not even exist.
hi, Siraj, thank you for your video, please explain how si 7:32 is calculated ? (aggregate score)
Great explanation!!
thanks!
1:25 Move 37 was not an invention of AlphaGo. The documentation says it was played by 1:10.000. Bcs the data based on 10.000 games from human amatures, the frequency was one of the human player out of 10.000 human players, which were the base data of AlphaGos learning pattern, which it could optimize but not surpass. That also explains the dead lumps in AlphaGos strategy.
Siraj is at his peak, making 4-5 videos per week.
Don't forget to sleep, Siraj :D
yes i need to chill but i'm too dedicated
The mentioned move 37 was played in game 2 of 5, which was streamed here: th-cam.com/video/l-GsfyVCBu0/w-d-xo.htmlh17m46s
At the bottom right of the video at 1:17:46 you can see that black (AlphaGo) is playing the 37th stone. The reaction of the moderators is funny :)
Siraj, you've improved your skill of teaching a lot over the years! Now, you talk more slowly and your videos are much more comprehensive than before! Beautiful. Keep going! :D
I have a question on "The outputs of neural network are: 1)possibilities for each next move and 2)possibility of win."
Does "possibilities for each next move" correspond to one-hot encoding for the next move?
Thank you! Somehow in every previous explanation I missed the fact that MCTS involved purely random playouts. As a Go player, it surprises me that purely random moves would be a good diagnostic for the goodness of a move. It makes sense that strong shape (for instance) would withstand a random barrage of stones better than weak shape. Perhaps the same goes for small territories vs. large areas, which could be why AG prefers quick territory over whole-board influence. Random playouts seem like they would be less effective in complicated fights, where there are several possibilities at the local scale, let alone the whole board, but am I correct that the layers of neural networks involve smaller portions of the board, and so it might be able to deduce the correct local sequence from fewer playouts than otherwise?
thanks for video, which microphone do you use ?
What I'm curious about AlphaGo, is if there's "hidden technology" on its making.
That is, I know the source is closed, but a lot of its designs are available in papers.
Would someone with enough resources be able to create his own version of AlphaZero without having to research new technology (i.e. just coding based on the papers)?
Diogo V. Kersting LeelaZero is open source version of AlphaGo, where computing power is crowd sourced.
can you do a video about AI natural language understanding, with all the data we have in books and on the web an algorithm using that data should be able to learn to understand language, how far are we in that area what are the main issues?
Thanks Siraj. I have been watching your content for like 1 years. You have become quite awesome educator. Good wishes.
How can you do hyperparameter optimization if it takes so long to train the network?
Ymi_Yugy Hyperparameter tuning is only for supervised learning .
Reinforcement learning is super dope , relying only on the algorithm and the training process to get better and better.
its another layer of training time indeed
Hello Siraj ! Thank you for the video ! I am a newbie here and I wanna build my own AI for Go. Do you think a genetic neural network approach can suit this application ? :D
sir,thnx 4 instr,many ppl begin playing chess/go by remembering win/draw patterns(if u place stones in certain position,ur opponent have no other choice but follow u,thus u can control the result),there r many books about these "patterns"& tactics,r they real tesed by ai?
Hi Siraj, I am a regular viewer of your videos. I like them. It would be great to see some videos on observational learning.
@Siraj what’s going to happen with your old block chain course on the school of ai ?
This is truly amazing... and very well explained. Thanks, Siraj!
"Descrete" and "perfect information" have switched explanations at 3:35
Siraj you are an absolute beast. Thank you so much for everything you do. You have been so helpful, and I am so thankful for your channel.
Good video to the right point of time, a nice explaination for what I am currently reading about RL (Sutton)
If human mind also has good capacity to traverse all possible state space(may be by tree search and others ) at the speed of computer processors/GPU, would it be that AI and human level would be the same on especially for the game like alphago?
what would than be the difference between humans and computers?
alpha zero doesnt go through all state spaces, this is impossible with current hw for games like chess or go
This video is amazing man thanks for explaining :)
Very scary. If the algorithm learns TCP/IP, HTTP, and such, any computer on the Net is pwned.
great video. what about chess? why so little information?
Is it open sourc? And if it is open source where can I get ot
Did we reach the i-Robot era already?😱 freaky stuff indeed!
How do you post so often. I love it. Keep it up Siraj!
how is your definition of "discrete" different from "perfect information"?
You can have discrete games with imperfect information: such as chess with invisible pieces or Space Hulk.
Great explanation! but no unlimited stones, a standard set includes 181 black and 180 white stones (361 intersection points)
Thank you for this Jucy video @siraj!!
i made at the end ..but have no idea what you are saying :)
Would AlphaGo Zero vs AlphaGo Zero end in a draw then?
Why do you keep trying to grab the air in front of you when saying hi ?
"Hey, I'm a beautiful wizard ya'll!"
yes you are love u
please make videos on feature engineering.
Hey Siraj, great video thow, I would recommend you that you don't animate every element on your diagrams with transitions, (feels a bit power pointy), instead just show the whole diagram (e.j. a neural network) and only highlight the piece of the diagram you are talking about, the same with the code, place as much code (or pseudo code) as possible, and highlight the important part(sometimes not even the whole line) as you mention it, I think that would make your explanations more clear, and visuals less distracting, but for the love of A.I., the memes, don't change them, they are great.
1:34 that's a meme right there.
"let's be real, probably some tea"
Why does he gasp for air between each sentence
I am a Master student of Machine Learning and Data Mining, I love your videos. I just have a small complaint that, it's sometimes hard to follow you when you're explaining really tough concepts. I know you have time constraints but it becomes nearly impossible to follow you in long explanations that you provide. If you could bring some pause between some really tough concepts, it will be little easy to follow you in better way.
Chemical Reaction Networks. Bio comp the next thing for sure.
thank you Mr.Raval
Awesomely Explained
Yay AlphaGo!!!! I love Go game , I want to reach dan level , I want to become 9dan professional
@surupendu , AlphaStill there
It is quite hard to understand the image channels made on a 19x19 board to get more accurate features to train.
Deep mind is really digging deep in mind
64 GPUs and 19CPUs cost millions of dollars? What? Did you mean 100k?
I have the same question: this result is based on TPU according to my information. Why only mention GPU en CPU? TPU cost more! about 10.000 $ for a unit, maybe. Titan V cost about 3000$.
over the very long period of time they trained it on, those costs really add up
Siraj do some videos on CYBORG plzzzzz
Epic content sir
IF YOU TAKE THIS---YOU WILL LOSE YOUR SOLE AND NEVER BE ABLE TO GOE TO HEAVEN EVER AGAIN
Need ur help Siraj
I am waiting for someone to develop Zola's algorithm 😈👹
Matrix reference at 3:48
thank you deepmind video
you should help promote Dataquest.io for everyone trying to get into A.I and data science its a great resource that truly allows anyone to get into the field.
"More possible Go positions then there are atoms in the universe" - isn't the universe supposed to be infinite?
it is, but that doesen't mean that there are in infinite amount of individual particles
right, but how does that make the number of Go positions larger than the number of atoms in the universe? You don't even know how many particles there are in the universe. At best, you can approximate the number of atoms in the observable universe and make your claim against that.
Paul Alexandru Pop actually we now that based on observable expansion of the universe
Paul Alexandru Pop he should have said, the known universe.
It's not known that the universe is infinite. In fact it is more likely believed to be finite, as we had a big bang and the universe expands from that moment, over a finite(but large) period of time
thank our AI god-masters -- may AlphaZero reign supreme -- that this video did not include tasteless royalty-free music to detract from the lesson
lol what if humans create a religion out of AI :D. wait. actually it sounds plausible :(
"Let's be real, probably some tea" XD
If AI system has way better than human beings, how possibly we human being maintain ruler of AI?
It's like ants create human beings.
I'm deep learner but still has huge conspicuous thoughts on safety of AI finally when we get into AGI period.
Have been four days, can I contact you in google+? or a mail please? I dont have a facebook acount
AlphaGo zero never play with a human player.
I'm having an anxiety attack...
It’s going to be ok. Life can be really hard but you’ll get through this
@@SirajRaval you are very nice
5:42
Just listen to 3:01-3:10 made my night so wet!!!!
when you don't have faith to find a hot girl even with AI ......😞
yes u can find a mate using AI
You could try the Monte Carlo method.
Could you redo this video, speaking more slowly? About 3 times more slowly? Thx ;)
don;t understand a thing you just said....
The problem is that a superior intelligence has no reason to share its intelligence with apes. Why on earth would it combine itself with us. We'll be pets in the best case scenario. Which isn't bad, I could live as a cat. Minus the neutering but I'm afraid there's no way out of that once it starts to genetically engineer us to be cuter and less violent.
Someone help me create an ai concept I have in mind. Ill pay you.
what is the concept?
Aman pradhan Give me a contact. I will explain it to you.
my email id is pradhanaman2595@gmail.com
AI won’t beat Zork though.
Could they put intelligence into playing a game like Star Citzen instead. Go is so boring 😴
transhumanismus is comming
FIRST