Publication

Universal Approximation Property of Hamiltonian Deep Neural Networks

Publications associées (29)

Short-term energy use prediction of solar-assisted water heating system: Application case of combined attention-based LSTM and time-series decomposition

With improved insulation of building envelopes and the use of low-temperature space heating systems, the share of energy use for domestic hot water (DHW) production in buildings has increased significantly, and nearly become the most energy-expensive servi ...

2020

Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

Michaël Unser, Harshit Gupta, Joaquim Gonçalves Garcia Barreto Campos, Shayan Aziznejad

We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that end, ...

2020

Geometric ergodicity for some space-time max-stable Markov chains

Erwan Fabrice Koch

Max-stable processes are central models for spatial extremes. In this paper, we focus on some space-time max-stable models introduced in Embrechts et al. (2016). The processes considered induce discrete-time Markov chains taking values in the space of cont ...

ELSEVIER SCIENCE BV2019

Sign-Changing Solutions for a Class of Zero Mass Nonlocal Schrodinger Equations

We consider the following class of fractional Schrodinger equations: (-Delta)(alpha)u + V(x)u = K(x)f(u) in R-N, where alpha is an element of (0, 1), N > 2 alpha, (-Delta)(alpha) is the fractional Laplacian, V and K are positive continuous functions which ...

2019

Biologically plausible deep learning – but how far can we go with shallow networks?

Wulfram Gerstner, Johanni Michael Brea, Bernd Albert Illing

Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining s ...

2019

Backpropagation-Friendly Eigendecomposition

Pascal Fua, Mathieu Salzmann, Zheng Dang, Yinlin Hu, Wei Wang

Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it with the Power Iteration method, particularly when dealing with large matri ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2019

Combining Multiple Views for Visual Speech Recognition

Jean-Philippe Thiran, Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazim Kemal Ekenel

Visual speech recognition is a challenging research problem with a particular practical application of aiding audio speech recognition in noisy scenarios. Multiple camera setups can be beneficial for the visual speech recognition systems in terms of improv ...

KTH2017

Generalized Poisson Summation Formulas for Continuous Functions of Polynomial Growth

Michaël Unser, John Paul Ward, Quy Ha Nguyen

The Poisson summation formula (PSF) describes the equivalence between the sampling of an analog signal and the periodization of its frequency spectrum. In engineering textbooks, the PSF is usually stated formally without explicit conditions on the signal f ...

2017

Word Sequence Modeling using Deep Learning : an End-to-end Approach and its Applications

Joël Yvon Roland Legrand

For a long time, natural language processing (NLP) has relied on generative models with task specific and manually engineered features. Recently, there has been a resurgence of interest for neural networks in the machine learning community, obtaining state ...

EPFL2016