Deep Learning session at NIPS 2017

Presentations from the Deep Learning session:

0:44 TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
14:52 Train longer, generalize better: closing the generalization gap in large batch training of neural networks
28:20 End-to-End Differentiable Proving
42:04 Gradient descent GAN optimization is locally stable
58:51 f-GANs in an Information Geometric Nutshell
1:05:15 Unsupervised Image-to-Image Translation Networks
1:10:52 The Numerics of GANs
1:14:44 Dual Discriminator Generative Adversarial Nets
1:19:29 Bayesian GAN
1:24:38 Approximation and Convergence Properties of Generative Adversarial Learning
1:28:39 Dualing GANs
1:32:46 Generalizing GANs: A Turing Perspective

Видео Deep Learning session at NIPS 2017 канала Steven Van Vaerenbergh