AI That Creates AI

Рет қаралды 106,662

6 жыл бұрын

How can we build AI that creates AI? This concept actually already exists! Google uses self-creating AI as part of its AutoML service that finds the best model for customers. Genetic algorithms and neuroevolutionary strategies offer us a way to replicate the process of natural selection en silico. I'll talk about ways of using machine learning algorithms to create better machine learning algorithms in this video.
Code for this video (with coding challenge):
github.com/llSourcell/neuroev...
Der Waldi's Winning Code:
github.com/DerWaldi/youtube-v...
Paramdeep's Runner up Code:
github.com/ParmuSingh/face_swap
Please Subscribe! And like. And comment. That's what keeps me going.
Want more education? Connect with me here:
Twitter: / sirajraval
Facebook: / sirajology
instagram: / sirajraval
More learning resources:
• AI Codes its Own ‘AI C...
• AI evolves to compose ...
• Art By Artificial Inte...
• Amazing! Conversation ...
• Google's DeepMind AI J...
gekkoquant.com/2016/03/13/evol...
Join us in the Wizards Slack channel:
wizards.herokuapp.com/
And please support me on Patreon:
www.patreon.com/user?u=3191693
Signup for my newsletter for exciting updates in the field of AI:
goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content! Join my AI community: chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available):
www.wagergpt.co

Пікірлер: 263

@SebiMu 6 жыл бұрын

Yeah coding challenge winner :) Thanks Siraj!

@SirajRaval 6 жыл бұрын

thanks for the submission! Looking forward to more

@markonfilms 6 жыл бұрын

Cloned your code and followed your instructions and it is absolutely awesome! I'm super impressed with the quality of your work. Also thank you for the comments in the code. It really helps when I try tweaks. I am looking into making this code properly scale on multiple GPUs. I see that Keras has a fairly simple way to implement this when using TensorFlow as the backend. I am having a tough time trying to figure out how to adapt this particular project to run on multiple GPUs however.

@SebiMu 6 жыл бұрын

Nice :) I am really excited what results you can get with that computing power. My first thought would be to simply split the two decoders on a gpu each, but I have absolutely no idea of multi GPUs.

@markonfilms 6 жыл бұрын

Der Waldi I've been playing with the code a lot and taking a crash course into Keras. I was able to get the model to technically run on all the GPUs but not with any real speed benefit. I also tried a script a found to split the batches up but it caused the tensor dementionality to go wrong in some way that wasn't apparently easy to fix. Another issue is that the training data for the faces I'm testing with right now aren't very large so there's less potential to optimize for multiple GPUs from what I've read. A single 1080 is actually fairly impressive to me in the results. So far I haven't actually finished training because I've been messing with parameters etc too much.

@JoswinConcessao 6 жыл бұрын

Next Video: AI that creates an AI which creates an AI

@tarunkashyap8515 6 жыл бұрын

inception AI

@JoswinConcessao 6 жыл бұрын

tarun kashyap haha

@SideControl 6 жыл бұрын

ACeption

@Bestname_Ever 6 жыл бұрын

Pure Motivation ERROR: AN ACEPTIONS HAS OCCURRED, RESTARTING WINDOWS

@2LegHumanist 6 жыл бұрын

It's not an AI that creates an AI.

@psinha6502 5 жыл бұрын

Why I watch these videos even though I understand a little bit is because I know someday these things will start making sense to me once I am done with what I am learning nowadays....And that drives me to learn things

@arthurvanderwal 5 жыл бұрын

Was expecting you'd sign off with 'but now I got to reproduce...' - awesome video as usual!

@fabdenur 6 жыл бұрын

Hi Siraj, I've complained a couple of times here in the KZfaq comments about you only including brief flashes of the results of the codes. Now it's my time to praise: in this video you included a full 20 seconds (from 8:23 to 8:43) of the neural net playing the game. It was very satisfying to get to appreciate the model in action. Congratulations and keep it up!

@KennethSaul 6 жыл бұрын

Every once in a while I run across a video that reminds me how uneducated I am. Thanks Siraj. Not to say that the presentation was bad or anything.

@Dude0413 6 жыл бұрын

I love to hear all these “THE END IS NEAR” people when we aren’t too close to AGI

@luck3949 6 жыл бұрын

Dude0413 My estimate to an AGI is 5-20 years, which is quite near.

@SirajRaval 6 жыл бұрын

Exactly, the comments are hilarious though

@AkashMishra23 6 жыл бұрын

Siraj Raval I, For One, Welcome our new AGI Overlords

@orion411 6 жыл бұрын

Never heard of Sirisys?

@RyanScottForReal 6 жыл бұрын

We don't need AGI to be threatened by AI. The AI just needs to learn that we re often the limiting factor in many things we want to improve, and it decides we need to be removed. Furthermore an AI doesn't need to be as smart as us to trick us. That is super easy to do.

@redsusoverparadise2700 5 жыл бұрын

Looked for this video because Justin Y. commented on "AI learns how to play Flappy Bird"

@tristant9686 6 жыл бұрын

I like the small summary at the end of your videos.

@dhrumilbarot1431 6 жыл бұрын

I just saw Josh tanenbaum's agi mit lecture and was thinking about it.....there you go lucky me!!!

@cientificamente3628 6 жыл бұрын

This comment is just to thank you for the great content you produced. I think, in a way, you're doing for the current generation of programmers what the creators of "The World of Beakman" did to my generation: they inspired kids and teens, showing that science can be diverted. Once again, congratulations on your great work!

@rabiielbeji8541 6 жыл бұрын

AI will create the best artificial doctors, developers, designers, artists, ... AI will create the new history of all logical sciences. Maybe, I wouldn't be present at this period of progress but I'm sure it'll do it!

@rabiielbeji8541 6 жыл бұрын

I know that current machines learning techniques and deep learning models still far to simulate all human activities. But we can improve the AI fields by inventing new technics inspired from neuroscience that consume fewer data and power and provide better accuracy

@rabiielbeji8541 6 жыл бұрын

of course *Simon*, you are right about the bad uses of the AI technologies like deepfake and it's a common problem for all technologies. I don't say it's easy, but just I have this dream how these technologies will facilitate our life in the future and current AI technics was just the first attempt. I respect your point of view my friend :-) ;-)

@Belofsky1 6 жыл бұрын

No it won’t.

@Belofsky1 6 жыл бұрын

Just splash a cup of water on it, problem solved. LOL

@0EEVV0 6 жыл бұрын

Simon WoodburyForget took 20 years to get decent NN, took us a lot of years of evolution.

@inquiremore1178 6 жыл бұрын

Hey there Siraj, I love your videos and they serve as a great inspiration for me to pursue an education in AI. One thing I'd like to mention though is I notice that your video has a fair bit of background noise. To avoid this, you can download Audacity (free software), which I use for the videos I've made, and use the noise reduction feature improve your sound quality even if your recording setup isn't perfect. Best of luck!

@moulikchaturvedi5407 6 жыл бұрын

Hey Siraj ! First off, I'm a big fan and love your work ! And what if we create a model which stores it's data collected on a graph and use random mutations to create a few offsprings of the model and choose the best model of them and repeat the process. That will be a genetic algorithm, right ? Will it be the right approach ?

@empretecasociados8090 6 жыл бұрын

y creeme que aprecio tus aporte y tus contenidos, pero también algunas veces también entiendo a tus detractores. Ellos son mucho más conservadores, creo que eso es porque están mas focalizados en el hacer hoy. contrario a ti que estas mas concentrado en comunicar en una visión "Janusvian" del problema (ver el pasado, presente y el futuro de la AI). Disfruto mucho tu forma de comunicar, es muy agradable e intrépida. Espero mas videos Gracias Siraj

@saveyourlifes7867 6 жыл бұрын

So, if I got it right, autoML is composed of two AI, the parent, and the child. The goal of the child is to have the lowest error rate on a given dataset. The role of the parent is to find the best architecture for the child so that its error rate is the lowest possible. But what do you exactly mean by "architecture"? Does it have the capability to add convolutions, LSTM... or does it only modify hyperparameters? How is it better than grid search?

@cod-newbie9166 5 жыл бұрын

I love your content, I just want to know if it would be ideal to use tensorflow to start ML without knowing how to code the neural network from Scratch?

@roguedrones 6 жыл бұрын

Siraj Raval, hardcore Ai genius.

@primalcam812 6 жыл бұрын

Yo, Siraj hittin the gym! LOL Nice man

@cashewfilms5372 4 жыл бұрын

"hello world! it's sirage!" me who had hell figuring out the basic console commands: aight ima head out

@PrafullaPallal 6 жыл бұрын

Good work. Do keep posting.

@Mukund568 6 жыл бұрын

Good stuff!

@DiamondTurtleGamer 6 жыл бұрын

I was waiting till this was going to happen

@zanderceo91 6 жыл бұрын

Did that music snippet say- drop it like a bot lol? Glad to see you appreciate rap culture. I dig it. Good content as usual.

@JazevoAudiosurf 6 жыл бұрын

good vid. i think this is one of the more interesting future topics if we want to build a human like brain one day

@_taylor_v 6 жыл бұрын

Is there a benefit to not using crossover of multiple "fit" models? I guess there are many different ways to implement genetic algorithms, but I've never seen one rely so heavily on only one fit member of the population and not at least a few for crossover. Interesting stuff! Nice video!

@RadhikaMeera 6 жыл бұрын

Hi Siraj, what I should the difference between AI, machine learning , deep learning . Do you have a video just like the one you had for machine learning in 3 months for AI

@larryteslaspacexboringlawr739 6 жыл бұрын

thank you for ai recursion video

@tsgbalakarthik Жыл бұрын

I love this video and you and the concept neuro evolution

@BlackXxScopez 6 жыл бұрын

Would it be beneficial to keep some momentum when performing gradient descent to avoid local minimums?

@subramanyam2699 5 жыл бұрын

This is insanely awesome..

@tylerknight99 6 жыл бұрын

"The core problem is finding the right hyperparameters settings that result in the lowest loss or the highest reward. The traditional way of doing this is with gradient descent which is called back propagation."

@SirajRaval 6 жыл бұрын

Meant to say parameters

@Euquila 6 жыл бұрын

Man, you are one smart dude!

@ozuwara1861 6 жыл бұрын

Siraj, if you touched neuroevolution please make a video on these "safe mutations" presented in Uber's paper

@vickyredwon 6 жыл бұрын

Siraj that creates siraj

@reyariass 6 жыл бұрын

How about an ai that builds the best looking and most fuel efficient rocket that can get to the mun in Kerbal Space Program?

@w.maximilliandejohnsonbour725 6 жыл бұрын

Interesting...!!!!!.

@DariusAlexanderMusic 6 жыл бұрын

Paramdeep Singh: Always the bridesmaid, never the bride.

@greenserpent7712 6 жыл бұрын

I was waiting for you to cover this! Nice!

@iprototypei6416 6 жыл бұрын

Hi Siraj, which machine learning framework can you consider ?

@TheZappingChannel 3 жыл бұрын

Wait, so the thing we optimize with GA are the hyperparameters or the trainable weights themselves?

@btouw8558 6 жыл бұрын

i am new to phyton, but you inspire me start relearning programming, what ide is free and most practical, icould not find in the playlists

@AnonymousAccount514 6 жыл бұрын

This channel is so awesome

@6lack5ushi 6 жыл бұрын

Great Video!!! Where do you see a mechanical engineers role in Machine Learning. Should we stick to what we know or try to branch into machine learning as well? A bit of it is taught to us. All the math you go through has been taught to us, if anything its easier lol. But should we invest time into learning how to implement models. I do because i enjoy it but should all mechs put some work into it? KR Ben

@sumitaggarwal9477 6 жыл бұрын

I loved this video..........but it would be really awesome if you could add a requirement.txt file to your repo.....will make it easier to run the code

@SirajRaval 6 жыл бұрын

Yo yo I will get on this good to see u

@Kaixo 6 жыл бұрын

I used Evolution to trail a neural network to play Snake, it's way better than when I did it using gradient descent... And It's easier to code.

@oscarmulin114 6 жыл бұрын

Gotta note that, genetic algorithms are a lot slower than backprop, especially when you use any significant number of neurons (around >100). As an another note, trying to reproduce neural nets with varying topologies usually does not give an offspring that's better than its parents, so topology numbers have to be fixed or else optimization space is too big. (But, maybe with modern hardware it will be fast enough, who knows?)

@Grepoan 6 жыл бұрын

I'm trying to find the 'winners' for the code competition in this video, so that I can learn some alternative techniques. But I can't find the 'next' video, because I did not load this from a playlist. Could you link to the 'next' video where you have the top two codes for this functionality? Thank you

@samzhao638 3 жыл бұрын

A.I. gives us an illusion of creativity. It have no idea when given a blank paper to come up with something. Keep in mind it is still a tool.

@Abdega 6 жыл бұрын

9:30 He has a perfect opportunity to have his username be “ParamDeep Learning”

@ShaikAsad 6 жыл бұрын

I was waiting for this video! Thanks! Why don't you rap anymore.

@SirajRaval 6 жыл бұрын

rap is coming more aggressive than ever

@ShaikAsad 6 жыл бұрын

Can you make a video on reading source code from github and completely solving a machine learning problem from start to finish?

@salmanfaroz2759 6 жыл бұрын

@simpleman5098 6 жыл бұрын

Can we build a shitcoin that creates a shitcoin?

@markonfilms 6 жыл бұрын

Simple Man that generates a supershitecoin

@Belofsky1 6 жыл бұрын

Yeah it’s called “SirajCoin”

@eav300M 6 жыл бұрын

We love Siraj ❤👏👏💪💪✌

@SirajRaval 6 жыл бұрын

Love u Edgar

@poxyu_was_here 6 жыл бұрын

very nice, very nice indeed

@forthtemple 6 жыл бұрын

If you were to use AutoML for image classification would it be using purely genetic algorithms or is it a combination of genetic algorithms and classic CNN gradient descent?

@bauwndule 6 жыл бұрын

Siraj Raval is God!

@watcher4075 6 жыл бұрын

I remember when Stewie from family Guy created an AI and that AI created another one.

@petrnejedly6592 6 жыл бұрын

Which genetic algorithm is the best for evolving NN?

@thunderzone1152 6 жыл бұрын

you should make an AI that can make a video about Deep learning and submit it

@artemkovera5500 6 жыл бұрын

I just was thinking about GAs for building AGI.

@TheStarCycle 6 жыл бұрын

Great video, but I believe NEAT might actually take 2 parents and generate offspring from them, as opposed to selecting just one parent, but I could be wrong.

@star277hk 6 жыл бұрын

your arm muscle looks bigger than before

@buenaventuralosgrandes9266 6 жыл бұрын

he probably doing weightlifting

@Mzulfreaky 6 жыл бұрын

He made an algorithm to properly get them gains

@huseyngadirov7658 6 жыл бұрын

He def uses a GAN

@OktoPutsch 6 жыл бұрын

It's a Washing Machine Learning problem. Shrinking in every way.

@andrewkiminhwan 6 жыл бұрын

Never Stop Learning! I'm talking to you Ais

@ayushpatel5033 6 жыл бұрын

Is this method more computation expensive than gradient descent?

@stavrospapadopoulos115 6 жыл бұрын

Why dont you give reference to the papers mentioned in the video? (Write them in the description)

@Partytron 6 жыл бұрын

neat

@xrayer4412 6 жыл бұрын

My mind is blown

@sunegocioexitoso 6 жыл бұрын

Plot twist: Siraj it’s an AI

@hitman779 6 жыл бұрын

Ok I still don't get it. Why use neuroevolutionary algorithms where you can use hyper-parameter tuning? CAn someone explain?

@CodeDham 4 жыл бұрын

Nice video #codedham

@octaviusdelmonte9019 4 жыл бұрын

Also known as: once thought "invaluable" programmers now made obsolete.

@igorboldysh2749 6 жыл бұрын

why do you have so many problems(green areas at the bottom of the screen) with picture in this video? Thnx 4 videos, btw

@bghack 6 жыл бұрын

Thank god some people listened to me when I was telling them about this 5 years ago. And only now I see my ideas stolen, but at least seeing them realized is nice ....

@lauriejmusic 6 жыл бұрын

9:02 - so gradient descent isn't computed for any of the population ? same for backprop ?

@descai10 6 жыл бұрын

Now make an AI that recreates itself but more efficient. Recursively.

@camdenparsons5114 6 жыл бұрын

hey siraj, lets see some more on techniques to learn more with less data. also if you haven't seen 'MIT 6.S099: Artificial General Intelligence' (im sure you have) you need to check that shit out.

@lucasf.8353 6 жыл бұрын

It begins lol

@diegoantoniorosariopalomin4977 6 жыл бұрын

I'm going to say it again , strong ai will be achieved by distributed neuroevolution

@artemkovera5500 6 жыл бұрын

Maybe. In fact, the biological brain is a product of evolution.

@luck3949 6 жыл бұрын

Diego Antonio Rosario Palomino I think program synthesis techniques will achieve AGI sooner then any variations of deep learning

@EmanuelSN 2 жыл бұрын

Yes. Yes. That's right, please allow AI to replicate themselves, nothing dangerous out here.

@2LegHumanist 6 жыл бұрын

This is just parameter tuning. Why are you hyping it?

@kalebrand 6 жыл бұрын

Because it's not just tuning parameters of a fixed architecture, it's also trying different network architectures and choosing the ones that perform best

@2LegHumanist 6 жыл бұрын

kalebrand Where did I use the term "fixed architecture"? The architecture itself is made up of a set of hyperparameters. It is not changing the underlying code or algorithm. It is not something that can lead to the next backpropagation or a new approach to neural network based predictive analytics. What it does is save a data scientist a bit of time and produces models with a couple of percent better accuracy than what humans have been able to do. It is a great achievement, but to call it AI creating AI is pure hype and clickbait.

@2LegHumanist 6 жыл бұрын

...and the fact that people commenting here equate this to kurzweilian self-improving AI just proves how irresponsibly misleading this turn of phrase is.

@kalebrand 6 жыл бұрын

That's a fair assessment. News and media surrounding AI/ML is almost always really misleading. All we have is algorithms that can minimize loss on a single objective, and that's all we're gonna have for quite some time. AI is just glorified linear algebra, and people are freaking out doomsday scenarios because they're being so misled.

@NoahHornberger 6 жыл бұрын

I think its because A is the first letter of the alphabet and I is the word we use to talk about ourselves. So it seems like something extra special just because of the letters and their over-interpreted meaning. If it was called SK or GX no one would be afraid. AI sounds like a creature with more sentience, but in truth there is no brain, nerves or even a center of awareness.

@diesel4338 Жыл бұрын

Its probably how computer components like CPU and GPU are made ....

@Maisonier 5 жыл бұрын

It's possible to create a kernel with AI?

@PhilippGrafendorfer 6 жыл бұрын

bizeps is coming!!!

@Aer0xander 6 жыл бұрын

When singularity?

@cristian-bull 6 жыл бұрын

Best performing model --> learning rate=0 ._.

@dzhiurgis 6 жыл бұрын

Salesforce had this for like 2 years or something

@dandanthedandan7558 6 жыл бұрын

Why not create an AI that created better AIs than itself? Keep the chain going and you'll achieve terminator-levels gods :D

@herbivorouscyborg2398 4 жыл бұрын

I'm struggling to understand how the "reproduction" step is supposed to work. How do you produce offspring which benefit from the parent's good performance while also mutating it to perform differently?

@zakariyamohamed6388 3 жыл бұрын

Is there any possible way that we can get A.i to teach human? I think it is possible 🤔

@Y2Kvids 6 жыл бұрын

So AI tests AI algorithsms ?

@madjoemak 6 жыл бұрын

I wish I was the one who designed neural networks... Sadly I'm not 😣

@amitkhopade9372 5 жыл бұрын

Create video on Facebook Stopped AI project, include why they stopped ,what was that ..?

@zdlax 6 жыл бұрын

Chillax guys. Self-aware AI is impossible and therefore it will never pose a threat to humanity. End statement.

@displayname8848 6 жыл бұрын

3:49 Limitations of the human mind

@ferus5583 6 жыл бұрын

Robots Gonna rule the world so soon....

@Luke7389 6 жыл бұрын

So if its like a ball rolling down it means there is gravity in an algorithm and AI finds the best way through it ?!?!

@RohanRaoisdabest 6 жыл бұрын

recursive AI

@lucav4045 6 жыл бұрын

all these comments about nasty killer robots destroying the world: stay cool, this will definitely not happen.

@__-tz6xx 6 жыл бұрын

It is actually getting annoying. Every single video about ML or other things in the realm of AI has some comments about killer robots destroying the world. If I talk in public then the first thing people think and reply back when I mention AI is something along the lines of: "The killer robots are coming" It seems like a naïve and pointless thing to say now.

@FG-Supercharged 6 жыл бұрын

Yeah it's always, "AI are going to destroy the world", never "AI are going to improve the world"! SMH...

@jeffsnox 6 жыл бұрын

Luca _is_ AI

@randompanda3415 6 жыл бұрын

Oh, if you say so.

@Euquila 6 жыл бұрын

If the AI can get into some kind of nanotech substance that gives it unbounded mobility, then I think we could have a problem if they have no emotional components. If AI has emotions similar to us, then we are probably OK.