223 citations · 324 across the 12 of their papers we have counts for
6 papers · 1 filter
No Representation without Transformation
Giorgio Giannone, Saeed Saremi, Jonathan Masci +1
We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the la…
Safe Interactive Model-Based Learning
Marco Gallieri, Seyed Sina Mirrazavi Salehian, Nihat Engin Toklu +4
Control applications present hard operational constraints. A violation of these can result in unsafe behavior. This paper introduces Safe Interactive Model Based Learning (SiMBL),…
SNODE: Spectral Discretization of Neural ODEs for System Identification
Alessio Quaglino, Marco Gallieri, Jonathan Masci +1
This paper proposes the use of spectral element methods \citep{canuto_spectral_1988} for fast and accurate training of Neural Ordinary Differential Equations (ODE-Nets; \citealp{Ch…
Recurrent Neural Processes
Timon Willi, Jonathan Masci, Jürgen Schmidhuber +1
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Giv…
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer
Jan Svoboda, Asha Anoosheh, Christian Osendorfer +1
This paper introduces a neural style transfer model to generate a stylized image conditioning on a set of examples describing the desired style. The proposed solution produces high…
Deep Iterative Surface Normal Estimation
Jan Eric Lenssen, Christian Osendorfer, Jonathan Masci
This paper presents an end-to-end differentiable algorithm for robust and detail-preserving surface normal estimation on unstructured point-clouds. We utilize graph neural networks…