140 citations · 375 across the 33 of their papers we have counts for
6 papers · 1 filter
On genuine invariance learning without weight-tying
Artem Moskalev, Anna Sepliarskaia, Erik J. Bekkers +1
In this paper, we investigate properties and limitations of invariance learned by neural networks from the data compared to the genuine invariance achieved through invariant weight…
LieGG: Studying Learned Lie Group Generators
Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik +1
Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symme…
PIE: Pseudo-Invertible Encoder
Jan Jetze Beitler, Ivan Sosnovik, Arnold Smeulders
We consider the problem of information compression from high dimensional data. Where many studies consider the problem of compression by non-invertible transformations, we emphasiz…
Asymmetric kernel in Gaussian Processes for learning target variance
Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders
This work incorporates the multi-modality of the data distribution into a Gaussian Process regression model. We approach the problem from a discriminative perspective by learning,…
i-RevNet: Deep Invertible Networks
Jörn-Henrik Jacobsen, Arnold Smeulders, Edouard Oyallon
It is widely believed that the success of deep convolutional networks is based on progressively discarding uninformative variability about the input with respect to the problem at…
Multiscale Hierarchical Convolutional Networks
Jörn-Henrik Jacobsen, Edouard Oyallon, Stéphane Mallat +1
Deep neural network algorithms are difficult to analyze because they lack structure allowing to understand the properties of underlying transforms and invariants. Multiscale hierar…