Banff
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
Neural Information Processing Systems http://nips.cc/
Initialization of ReLUs for Dynamical Isometry
Rebekka Burkholz, Alina Dubatovka
Deep learning relies critically on good parameter initialization prior to training.
Explanations can be manipulated and geometry is to blame
Ann-Kathrin Dombrowski, Maximillian Alber, Christopher Anders, Marcel Ackermann, Klaus-Robert Müller, Pan Kessel
Neural Information Processing Systems http://nips.cc/
Variational Temporal Abstraction
Taesup Kim, Sungjin Ahn, Yoshua Bengio
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data.
MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
The greater the color contrast, the lower the dimensional feature similarity.
Unsupervised Causal Generative Understanding of Images
We present a novel framework for unsupervised object-centric 3D scene understanding that generalizes robustly to out-of-distribution images.
Nonparametric_Uncertainty_Quantification_for_Single_Deterministic_Neural_Network (1)
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions.
A Quantitative Geometric Approach to Neural-Network Smoothness
We implement the algorithms induced from this quantitative geometric approach, which are based on semidefinite programming (SDP).