Keras Explained

Whats the best way to get started with deep learning? Keras! It's a high level deep learning library that makes it really easy to write deep neural network models of all sorts. It can use several popular backends like Tensorflow and CNTK. I'll show you how it works and explain how it compares to the other deep learning libraries.
Code for this video:
github.com/llSourcell/keras_e...
Alberto's Winning Code:
github.com/alberduris/Reinfor...
Sven's Runner-up Code:
github.com/EmbersArc/PPO
Please Subscribe! And like. And comment. That's what keeps me going.
Connect with me:
Twitter: / sirajraval
Facebook: / sirajology
Instagram: / sirajraval
More learning resource:
elitedatascience.com/keras-tu...
keras.io/
machinelearningmastery.com/tu...
github.com/fchollet/keras-res...
www.datacamp.com/community/tu...
dashee87.github.io/data%20sci...
Join us in the Wizards Slack channel:
wizards.herokuapp.com/
And please support me on Patreon:
/ sirajraval
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

[@raekm]

Suddenly all videos I search in KZbin start with "Hello World, it's Siraj". Thanks for the amazing content

[@prestocranius7627]

Thank you so much siraj for making this. I asked you this on your twitter handle, and I dont know if you made this based on my tweet, but want to believe you did and I am grateful. Thanks a tonnnn.

[@Shadeewolf]

Sweets exactly what i just came to your channel for!

[@vikbehal]

Any recommendations on how to work on algorithm and data-structure required for ML/DL?

[@ladjiab]

Finally, Machine Learning related video. Thanks Siraj . @BerteADA

[@SirajRaval]

you got it, more coming

[@brajeshkokkonda]

Thank you Siraj ! How do I extract digits from any image?

[@EdrisSaberi]

Wonderful video, as always, thank you, Siraj.

[@rodrigomann]

@alberjumper Alberto Blanco Garcés, you are the man! First the stok market prediction, and now there you are again. Good job.

[@meghachovatiya1834]

Amazing Video! So much of info in very short time! Thanks!

[@rahulkrishnan529]

6:40 and onward helps with building a sequential network yourself. Thanks Siraj.

[@UsmanAhmed-sq9bl]

Awesome Siraj ! Excellent explanation ! Keras is the best library to build deep nets. Please do mention some thing about coming video.

[@snzn3854]

@Siraj Raval - Do you not do anymore live streaming tutorials? Also it would be very interesting to see you do a deep-learn learning tutorial using kaggle's dataset and actually competing on kaggles while live streaming.

[@SirajRaval]

i will do more live streaming soon

[@nartb]

So which part of this is actually different from PyTorch?? I've worked with it a bit and it seems like this is fairly similar so wanna see if I'm missing something. Thanks :)

[@JasonWhittle1]

Thanks Siraj. I love your video's man.

[@irqr4801]

Hi Siraj. I'm new to this, so I run the code in terminal and in the end like you showed in the beginning nothing will pop up to show a text and in terminal after the epoch 60 the texts still don't make any sense. Am I missing something?

[@vinay1744]

You made my day .... Just wondering when you would post this.. Keras..

[@skr_8489]

Where are dataflow modular visual frontends like dsprobotics Flowstone (formely Synthmaker) for signal processing?

[@subhokarmakar7065]

I can only say, Thank You for the help!!

[@netochidozie5528]

Dear Siraj do need to study maths or compter sceince in school in other to do machine learning or programming

[@pankajkumarmakwana3527]

Buddy how do get so much energy to teach us all this? You are really awesome. 😎

[@johnhammer8668]

The ending was awesome.

[@leowiniecki9264]

What's up with second order optimization in 2k18?

[@mohamedathilsafrasu.z678]

Scene classification possible in tensorflow

[@KehongGong]

Hi, May I ask anyone ever tried using Mac pro's Anaconda to run keras tutorial? either in jupyter or spyder, the keras always error when plot training history. Same setup, ubuntu 16.04 works fine, and virtual environment on Mac Jupyter notebook is okay.

[@ygpsk3860]

Is it ok to install keras and tensorflow on a regular macbook, or are GPUs necessary?

[@ShaikAsad]

Yulia Gri You can install it and if you don't have a gpu train them on floydhub

[@loganathansiva7063]

Thanks Siraj for your nice videos. Good luck keep going.

[@shreyanshvalentino]

Awesome video, and congrats people on comments, your counting is effed up

[@SirajRaval]

haha always

[@smtabatabaie]

But how about TFLearn? isn't it the best option to use with Tensorflow?

[@SirajRaval]

not maintained well enough

[@cptechno]

Can you please explain the term DEEP LEARNING. How do you recognize something that is DL or something that isn't DL?

[@atikkhatri6942]

This is true advice Siraj. Keras is the best way to deep dive into deep learning. I recommend to read "Deep Learning with Python" book by the Author of Keras himself (françois chollet). Pretty much deep content with many real use cases.

[@yeetusfetus8687]

this is really helpful!

[@tigjuli]

Very good content! love it!

[@gorannovaks]

can you do a lesson about locomotion based on reinforcement learning?

[@venuturumillisitaramarao2533]

Awesome video Siraj ....

[@saminchowdhury7995]

Sir can you please please do a series on Pytorch. It is such a powerful and promising library and it would be a great addition to your channel and great learning material for us

[@foobars3816]

Why did he say that thing about Microsoft? I didn't get that joke? Is this referring to the processor bugs that they only recently released security fixes for? I'm confused.

[@obinnaokafor6252]

Hatred

[@jamesbarker6373]

What does he mean by not using Microsoft products at the end of the video?

[@guadybird4266]

@9:19 >> “Deep Learning is Sexy for a reason!” … I love the face of Support Vector Machines!!!

[@lucasmagalhaes1286]

Is Keras really easier for beginners than TF-Learn?

[@jinxblaze]

yes

[@apetrenko_ai]

nah, same

[@bem7069]

Yeah, i've used to do a lot of stuff and it's quite easy to use.

[@SirajRaval]

yes

[@PatrickBateman12420]

@Siraj, awesome as always. Little slip "AlphaGo" was in 2015, not 2017 ....

[@jayjoshi9834]

awesome video, siraj bhai....but you need to use proper chroma key to properly subtract you from background

[@ChaiKirbs]

Please, don't advertise in the comments.

[@SirajRaval]

yes i will for sure and thanks

[@biomerl]

I think your best bet is to use numpy (which just does matrix multiplication if you're really really beginning) to start with. Simple, but requires you understand the mechanics to make it work. I started learning to program in C, in much the same way, and starting from the bottom like that, I feel, has helped me greatly.

[@thisismyalias]

Agreed.

[@SirajRaval]

my build a neural net in 4 minutes video does this, would be a great resource

[@muhammadsami7711]

You are totally right but if you want to test different models quickly and want to make a quick project. I would recommend using Keras. The real fun, though comes from making a Neural Net yourself.

[@jameslay6505]

It's funny how we train machine learning models so differently than we train ourselves. We tend to think it's best to learn from sophisticated explanations at the base level and build our understanding up from that, but we underestimate our ability to innately infer the inner workings of a topic from numerous excellent examples. I learned programming starting with high level languages, without reading a text book, and worked my way down to assembly, then to CPU design using HDL, then back up. I like this because A. it's fun to get stuff done, then B. it's fun to learn how the stuff works under the hood once you know what it's capable of, then C. you understand the whole stack differently. It's a hard sell when we begin with "okay, let's learn what NAND is" when you're like "how is this going to help me make a video game" or whatever.

[@blackmambagyn]

"I've gotta not use anything made by Microsoft!" smartest phrase I've heard this year.

[@poopcatapult2623]

I disagree. I know they used to be really bad especially regarding security but they did a 180 turn with Nadella and produce quite a few infesting pieces of technology. They also participate in open source development and contribute good code. They don't deserve this hate anymore.

[@nufosmatic]

Does Microsoft actually make anything? It was my understanding they stole everything...

[@pharoah327]

@@nufosmatic You're thinking of Apple, lol.

[@bem7069]

Dude! That was a cool video.

[@wolfisraging]

For learning, I'd say go and implement model from scratch using just numpy. And for production, you can use any higher level library like keras, tensorflow, pytorch, mxnet............ If u use those high end frameworks as beginner then you'd probably gonna be unknown of what actually is going on behind the scene. That's just my suggestion, I have faced it.

[@wolfisraging]

@@SimonWoodburyForget u r comparing sorting algorithm with ml, dl????? R u out of your mind?????? People who are afraid of scratch implementation don't deserve ml and dl.

[@ferrii7]

@@wolfisraging lol people deserves or not deserves haha ok guardian of dl

[@wolfisraging]

@Shubham Dhingra , unfortunately for you.... yes

[@wolfisraging]

@Shubham Dhingra but also definitely not necessarily, you can use tensorflow to calculate gradients

[@asciidiego]

In the Machine Learning course of Andrew Ng you have to do it all from scratch. Then in the specialization you use raw Tensorflow and later on in the specialization you use Keras. Also... Many deep learning fathers agree that that is a good methodology, e. g. Ian Goodfellow and the very same Professor LeCunn.

[@huimingsun3319]

thank you.your voice and video is really goodq

[@jitenSSP]

Is there an English version?

[@Zorn101]

Siraj are you an A.I?

[@SirajRaval]

not yet

[@onewhoraisesvoice]

Siraj, explain us an Apache UIMA, please

[@erwinrommel5593]

Hi am new to this stuff could u kindly tell me are there any free courses available to learn this stuff

[@MarkJay]

I total agree. Keras is great to get started with. Pytorch sounds great but it doesn't seem to have windows support yet.

[@TheAcolossus]

it does now :)

[@kailashntalreja]

Awesome Video!!

[@kamikaze9271]

Microsoft has become a lot better after Steve Ballmer left

[@wiseversa5369]

Or after Satya took over

[@Ant-xz6he]

I just installed Keras and I come on here to see this. Today is gonna be a good day.

[@SirajRaval]

no need to use my ak

[@gorannovaks]

Congratulations. I still can't refuse myself using C# and visual studio..

[@NghiNguyen-ug8ur]

when 1080p look like 360p, great content but upgrade your camera, bro!

[@myselfremade]

"and for now, I've gotta not use anything by Microsoft" such an amazing signoff

[@pritishjaiswal8580]

Thanks siraj

Keras also have the Functional API, which I prefer using.

[@edreesfeda9266]

Thank you so much

[@praneshchandrasekaran9781]

Hey siraj, I'm a mechanical student, is it easy to me to learn deep learning

[@jyotipch]

so good that we are back in AI. I was getting so tangled in the block chains.

[@SirajRaval]

more AI coming

[@Change-Maker]

What about AI based block chains. E.g. skychain

[@binnyarora1219]

please make a video on spectre and meltdown

[@yousifahmed257]

very very very very very interesting

[@akashkandpal1832]

input times weight add bias activate ......remembered

[@SirajRaval]

hi akash thanks

[@akashkandpal1832]

thanks siraj for so informative videos

[@FuZZbaLLbee]

Why so happy about Theano stopping in 2018?

[@JohnEthan777]

FuZZbaLLbee Yeah, I think it was because its hard to use but it would have been nice if he indicated why

[@FuZZbaLLbee]

Ethan9750 I think there was a pydata talk where the speaker prefered it over tensorflow because it allowed to change the framework code more easily.

[@SirajRaval]

theano requires some absolutely insane configuration and installation (and compilation) of many third party libraries

[@AyeshaAhmad92]

I went crazy trying to get the configurations right for theano to run! Did not like it!

[@larryteslaspacexboringlawr739]

thank you for keras video, love your final line of video, i am jelly of your independence from the bloatware monopoly company that shall not be named

[@georhodiumgeo9827]

I agree except you forgot planned obsolescence.

[@vijaymanoharan2998]

sirajcoin to the moon

[@crosstuck]

Happy new year siraj #Tyler #TeamTyler

[@wolfisraging]

U r best

[@kunalr_ai]

Thanks for free education

[@anandnatarajan7114]

fantastic information for a person know nothing about deep learning! one feedback would be - information flowing too fast and I had to watch multiple times to understand better. may be it just me, otherwise I love it.

[@PromethorYT]

You should make a neural network that can crop out your green screen better in-real time.

[@novovires5625]

I do think it's an old video from your Playlist of Machine Learning.

[@bhavykhatri2669]

At 4:01 captions are showing chaos instead of keras

[@nufosmatic]

Artificial Stupidity in action...

[@user-es8qx5uj2h]

exactly 200,000 views, congrats

[@JT-iw2cw]

Viola came to party!

[@tonycatman]

"The question I get asked the most is..." I don't believe this. I reckon people ask you whether you argue with your hair.

[@marioandresheviacavieres1923]

thanks! :)

[@seraph1890]

can you do a neromation ico review

[@jigonro]

What is up with your hate towards Microsoft?

[@moleculist7978]

if you have to ask...

[@cfsantos85]

Keras is REALLY good but there is a negative point: if you need to use a custom loss function, it become a pain in the a**. I have been trying to implement YOLO loss function and I really don't know how to do it. Besides that, it is very cool!

[@yazdipour]

9:15 I've gotta not use anything made by Microsoft Me: Meh :/

[@shaswatsood4595]

You r best

[@SomebodyOutTh3re]

you are theNewBoston of AI

[@raisshaikh259]

super se uper

[@louerleseigneur4532]

merci

[@atifadib]

Why you hate microsoft bruh?

[@akashkandpal1832]

Siraj Videos comes like Aamir Khan's Blockbuster movies

[@joshsmit779]

Hello World it's Keras

[@bauwndule]

Thanks for making deep learning accessible for idiots like us. :")

[@PlayTheMind]

Keras? More like KerYAAS!

[@sabarimanoharpalaniappan2442]

Caffe2, please...!

[@nickellis1553]

Yeeeeesss!!!

[@SirajRaval]

back to AI

[@sunnybeta_]

This was exactly what i needed omg i love you

[@SirajRaval]

love you

[@dustinandrews89019]

Re: Coding Challenge. I've already got one I'm working on. DDPG network that learns a grid world game. github.com/dustinandrews/machinelearning/tree/ddpg-link-gradient/DDPG , Some features: epsilon is dynamic, the better the agent is doing the less randomness in the actions. The simulation supports curriculum training where you can set how far away from the goal the start position can be. agent_play(ddpg) pops up a window and shows how the agent plays the game for one episode.

[@SirajRaval]

great work Dustin love the choice of grid world!

[@dustinandrews89019]

Thanks! Sorry the code is such a mess. Once I get it all working I'll clean it up and make a repo for it. My critic is learning well, but the actor is still struggling.

[@deepmlpython1500]

Create video, i love how to explain and the energy you have. thank you

[@fitmachinelearning352]

My Entry. Ours is a new efficient and intuitive algorithm that performs well in continuous action space. It's called Selective Memory. You can see a demo of it here kzbin.info/www/bejne/nnzVd3mbj9akaac

[@guitarheroprince123]

you could change the title to "how to get started with deep learning (with keras)"

[@anubhavbhattacharya6216]

Siraj, there's now an easier way - brain.js! It would be great if you could check it out!