20180215_MLKitchen7_YoheiKIKUTA

Talk at https://cookpad.connpass.com/event/77344/

Transcript

1. NIPS 2017 report Yohei KIKUTA resume : https://github.com/yoheikikuta/resume twitter: @yohei_kikuta (in Japanese) 20180215 ML Kitchen #7 1/23
2. What is NIPS? Neural Information Processing Systems (NIPS) - originally started as a meeting on NN - is one of the top conferences for theoretical ML 2/23
3. Statistics of NIPS 2017 3/23
4. # of registrations 4/23 year
5. 5/23 Log10(# of registrations) year
6. # of submitted papers 3,240 6/23
7. Algorithms Deep Learning 7/23 Research topics
8. # of accepted papers 679 8/23
9. acceptance rate 21% papers not posted online: 15% papers posted online: 29% 9/23
10. JSAI top conference reporters I attended NIPS as one of the reporters. 10/23
11. JSAI top conference reporters I attended NIPS as one of the reporters. It’s me. 11/23
12. Views of the conference 12/23
13. Invited talks 13/23
14. Sponsors 14/23
15. Exhibitions 15/23
16. Poster sessions 16/23
17. Interesting topics 17/23
18. Trends - GAN - Theoretical understandings of DL optimization - New directions of DL - Interpretablities of ML - Incomplete information games - Deep Reinforcement Learnings - Bayesian Deep Learnings - … 18/23
19. GAN: convergence around equilibrium points Convergence analysis of GANs - analysis near equilibrium points - ODE analysis of gradient flows - relation to eigenvalues of Jacobian double back prop. regularization 19/23 ref: https://arxiv.org/abs/1705.10461 https://arxiv.org/abs/1706.04156
20. GAN: an example of application 20/23 ref: https://arxiv.org/abs/1705.09368 Toward practical applications. Combinations of models and conditional “constraint”.
21. Understandings of DL: generalization 21/23 ref: https://arxiv.org/abs/1705.08741 https://arxiv.org/abs/1710.06451 https://arxiv.org/abs/1706.02677 SGD optimizations are controlled by “noise scale”: ε : learning rate, N : training set size, B : Batch size training error
22. New DL architecture: CapsNet 22/23 ref: https://arxiv.org/abs/1710.09829 https://www.oreilly.com/ideas/introducing-capsule-networks A kind of vector generalizations of neurons. - a new look of object recognitions - routing mech. to capture relations btw capsules - robust to overlapping and affine transformations capsule dim.
23. New DL architecture: Deep Sets 23/23 ref: https://arxiv.org/abs/1703.06114 A model that is invariant under permutations: text input image input Digit summation experiments