GAN and Quantum

Talks about Generative Adversarial Networks, Machine learning and quantum

1. GAN
Rajesh Jeyapaul
Sr. Developer Advocate and AI Architect , IBM India

2. Fake vs Real

3. ICLR2019 talk by
Ian GoodFellow

4. ICLR2019 talk by
Ian GoodFellow

5. ML vs Adversarial
•Value function –not cost function
•Min-max
•Player1 wants to mimimisethe winning option of player2 , player2 want to maximize the winning option
•Player 1 looking for local minima , player 2 looking for local maxima
•Nash equllibrium
•Each player is assumed to know theequilibriumstrategies of the other
players

8. ICLR2019 talk by
Ian GoodFellow
Progressive GAN
2 representative models created from celebAdataset
Take the sample and learn the probability distribution-
generate new samples from the same distribution
•Statistically same as the personalities in the training
data

9. How GAN works –2 player minimax game
•

10. 2 player minimax game
•Player 1 –Generator creates images
•Player 2 -Discriminator –recognizes the input as real or fake
•Adversarial competition on how to classify the fake samples generated by generator . Generator tries to adapt the input to discriminator to cause it to be misclassified. Discriminator tries to correctly classify fake as fake / real as real
•NASH Equllibrium
•Generator recovers the data distribution correctly
•Discriminator random guess whether the input is real or fake
•Practically reaching NASH equilibrium is not possible but we have reached to a place where we can generate realistic samples

12. Generating face is relatively easy –BIG GAN
made it possible with imagenet

13. Advantage –able to learn with less
supervised
•Converting day scene to night scene
•Unsupervised image to image translation

18. Challenges –Instability during training

19. Challenges –mode collpase

20. QUANTUM GAN
•DENSITY MATRIX –STATES (possible
configuration of Q system
•Quantum distribution
•Quantum superimpositionvsclassical
uncertainity(undoispossible)

22. Quantum generative adversarial learning
•https://arxiv.org/abs/1804.09139