Search Results for author: Sebastian Urban

Found 8 papers, 4 papers with code

Gaussian Process Neurons

no code implementations ICLR 2018 Sebastian Urban, Patrick van der Smagt

We propose a method to learn stochastic activation functions for use in probabilistic neural networks.

Bayesian Inference Gaussian Processes

Gaussian Process Neurons Learn Stochastic Activation Functions

no code implementations29 Nov 2017 Sebastian Urban, Marcus Basalla, Patrick van der Smagt

The proposed model can intrinsically handle uncertainties in its inputs and self-estimate the confidence of its predictions.

Bayesian Inference Gaussian Processes

Automatic Differentiation for Tensor Algebras

20 code implementations3 Nov 2017 Sebastian Urban, Patrick van der Smagt

For the function $f_{ij} (x) = x_i^2$, the derivative of the loss is $(dx)_i=\partial l/\partial x_i=\sum_j (df)_{ij}2x_i$; the sum is necessary because index $j$ does not appear in the indices of $f$.

Theano: A Python framework for fast computation of mathematical expressions

1 code implementation9 May 2016 The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang

Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.

Dimensionality Reduction General Classification

A Differentiable Transition Between Additive and Multiplicative Neurons

no code implementations13 Apr 2016 Wiebke Köpp, Patrick van der Smagt, Sebastian Urban

Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform.

A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions

1 code implementation19 Mar 2015 Sebastian Urban, Patrick van der Smagt

Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform.

Unsupervised Feature Learning for low-level Local Image Descriptors

no code implementations14 Jan 2013 Christian Osendorfer, Justin Bayer, Sebastian Urban, Patrick van der Smagt

Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision.

Binarization General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.