Tree-based demappers for multiple-input multiple-output (MIMO) detection...
Simulated annealing (SA) is a stochastic global optimisation technique
a...
Neural networks are increasingly being used to solve partial differentia...
This paper introduces MDP homomorphic networks for deep reinforcement
le...
We introduce the SE(3)-Transformer, a variant of the self-attention modu...
Attention mechanisms, and most prominently self-attention, are a powerfu...
We introduce deep scale-spaces (DSS), a generalization of convolutional
...
Recent work (Cohen & Welling, 2016) has shown that generalizations of
co...
The Pix2pix and CycleGAN losses have vastly improved the qualitative and...
Semi-supervised learning (SSL) partially circumvents the high cost of
la...
Deep feature spaces have the capacity to encode complex transformations ...
Translating or rotating an input image should not affect the results of ...