Siraj Raval
This episode of Fresh Machine Learning is all about a relatively new concept called a Generative Adversarial Network. A model continuously tries to fool another model, until it can do so with ease. At that point, it can generate novel, authentic looking data! Very exciting stuff.
The demo code for this video is a set of adversarial Gaussian Distribution Curves in Python using Theano and PyPlot:
https://github.com/llSourcell/Generative-Adversarial-Network-Demo
I created a Slack channel for us, sign up here:
https://wizards.herokuapp.com/
I introduce two papers in this video
Generative Adversarial Networks:
https://arxiv.org/pdf/1406.2661v1.pdf
and the associated code:
https://github.com/goodfeli/adversarial
Generative Adversarial Text-to-Image Synthesis:
https://arxiv.org/pdf/1605.05396v2.pdf
and it’s associated code is here:
https://github.com/reedscot/icml2016
Another really cool repo using GANs:
https://github.com/Newmu/dcgan_code
Great explanation of GANs:
Live demo of a GAN:
http://cs.stanford.edu/people/karpathy/gan/
One more really great description of generative models:
https://openai.com/blog/generative-models/
I love you guys! Thanks for watching my videos, I do it for you. I left my awesome job at Twilio and I’m doing this full time now.
I recently created a Patreon page. If you like my videos, feel free to help support my effort here!:
https://www.patreon.com/user?ty=h&u=3191693
Much more to come so please subscribe, like, and comment.
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Hit the Join button above to sign up to become a member of my channel for access to exclusive content!
Source
i don't understand as single word 🙁
Why do my beliefs that I have learn something about AI desappear when I watch one of your videos?
thanks, this video so much time
Hi Siraj, Your videos which were LIVE on the Deep Learning Playlist, do not have any option to comments…
Also, for the GAN style transfer code, i am facing this issue … on line…
rec_z = inference_network(p_x, latent_dim, n_layer_inf, n_hidden_inf, eps_dim )
ValueError: Variable inference/Repeat/fully_connected_1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope?
Great job, nice explanation!
Siraj Man, you are gooooooooood . You explain so so well. v. Impressed !
thank-you!
How is that Intelligence?
What is foxhound?
Awesome Vidos. So much informative. Thanks
HMM is nit discriminative model
Are you Indian?
wow!
0:25 thank god you don't live in Scotland
TOOOO FAST…. ? ?
Awesome Bro. You Github is when developer is serious and focused. youtube is for watching during comute. Awesome man.
siraj how do you know where I can go tot learn about a "GAN" that can be used for drug discovery?
I wonder, how much training data is (was) needed to create those photo realistic images? I'd like to try some GAN work recreationally on different types of data and I am curious about the data I would need
siraj, you are fuckkkkkking awesome man. keep up the good work.
1:09 RIP Tay
That final joke gave me cancer.
But I love you, Sir.
hello i am fred, how aren -t you you tragener, frischnot the albane. snokkaka ante you?
awesome (y)
Thanks Siraj for this video! But I have a question about GAN, how does the discriminator improve the results of the generator? I can't understand the link between the output of the discriminator and the input of the generator, how the D is affecting the G. Can you explain this please?
@ 0:30 "models like support vector machines, neural nets and HIDDEN MAKOV CHAIN". I thought they(HMMs) were generative being the sequential versions of navie bayes that they are.
Any idea how to install Foxhound on Anaconda? pip didnt work
Braingasms ? ?