Deep Learning
A unified theory for the origin of grid cells through the lens of pattern formation
Ben Sorscher, Gabriel Mel, Surya Ganguli, Samuel Ocko
Neural Information Processing Systems http://nips.cc/
A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
Jeffrey Chan, Valerio Perrone, Jeffrey Spence, Paul Jenkins, Sara Mathieson, Yun Song
Neural Information Processing Systems http://nips.cc/
Riemannian batch normalization for SPD neural networks
Daniel Brooks, Olivier Schwander, Frederic Barbaresco, Jean-Yves Schneider, Matthieu Cord
Inourarticle, weintroduce aRiemannian batch normalization(batchnorm) algorithm, which generalizes the one used in Euclidean nets.
Recurrent World Models Facilitate Policy Evolution
Neural Information Processing Systems http://nips.cc/
An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
The inferred belief context can be leveraged to augment the state, leading to a policy that can adapt to abrupt variations in context.
