Surya Dantuluri's HAILCon Presentation on GANs alongside Jeff Dean (Google Senior Fellow), Peter Norvig (Director of Research @ Google), and Stefano Ermon (Professor @ Stanford University)
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
HailCon
images, notes, misc.
Generative Adversarial Networks.pptx
LICENSE
README.md
gany.png

README.md

Generative Adversarial Networks

Surya Dantuluri's Speech on Generative Adversarial Networks and It's Implementations Notes and Supplementary Material

I spent around 20 hours (I was given 24 hours notice on my speaking position) during the weekend before finals, and I haven't changed a lot of the work I presented(I started from nearly no knowledge on machine learning). If you'd like to make any suggestions, you can do that here: http://bit.ly/hailcongancomment#

Basic idea of a GAN

Here are some unformatted notes and citations(which I will format in the upcoming days)

0.0002 learning rate), come on the network cant really memorize at this stage. DCGAN

When you have a lot of neural networks (multilayer) that’s called deep learning

https://arxiv.org/pdf/1511.06434v2.pdf

Stuff to look at: https://github.com/hanzhanggit/StackGAN https://github.com/LantaoYu/SeqGAN https://github.com/SKTBrain/DiscoGAN https://github.com/stormraiser/GAN-weight-norm --weight normalization is better than batch normalization http://cs229.stanford.edu/notes/cs229-notes2.pdf

https://arxiv.org/abs/1703.10717--training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training

https://adeshpande3.github.io/adeshpande3.github.io/Deep-Learning-Research-Review-Week-1-Generative-Adversarial-Nets

different ways of convolution arthemetic https://github.com/vdumoulin/conv_arithmetic

examples: https://github.com/adeshpande3/Tensorflow-Programs-and-Tutorials https://github.com/platers/Logograms-GAN https://github.com/rrichajalota/generative-adversarial-networks https://github.com/jwilber/Semi-Supervised-Learning-with-GANS https://www.youtube.com/watch?v=9c4z6YsBGQ0&feature=youtu.be https://github.com/osh/KerasGAN http://cs.stanford.edu/people/karpathy/gan/

collection of gans: https://github.com/wiseodd/generative-models

good examples of networks/ neural networks with pytorch https://github.com/MorvanZhou/PyTorch-Tutorial same thing as above but with tf https://github.com/MorvanZhou/Tensorflow-Tutorial

bibliography: http://cs231n.github.io/convolutional-networks/#fc --used images http://kvfrans.com/generative-adversial-networks-explained/ https://datascience.stackexchange.com/questions/6107/what-are-deconvolutional-layers http://bamos.github.io/2016/08/09/deep-completion/ http://sites.nicholas.duke.edu/statsreview/probability/jmc/ https://clubpenguincheatsforyou2.wordpress.com/club-penguin-myths-and-rumors/ http://www.clipartpanda.com/categories/money-clip-art-free-printable https://www.quora.com/What-is-the-difference-between-conditional-probability-and-joint-probability http://slideplayer.com/slide/4877699/ http://www.kdnuggets.com/2017/01/generative-adversarial-networks-hot-topic-machine-learning.html