Universal Approximation Property of Hamiltonian Deep Neural Networks

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper presents an acoustic impedance control architecture for an electroacoustic absorber combining both feedforward and feedback microphone-based strategies on a current-driven loudspeaker. Feedforward systems enable good performance for direct imped ...

The great potential brought by large-scale data in the humanities is still hindered by the time and technicality required for making documents digitally intelligible. Within urban studies, historical cadasters have been hitherto largely under-explored desp ...

We develop an efficient computational solution to train deep neural networks (DNN) with free-form activation functions. To make the problem well-posed, we augment the cost functional of the DNN by adding an appropriate shape regularization: the sum of the ...

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 ...

The minimization of a data-fidelity term and an additive regularization functional gives rise to a powerful framework for supervised learning. In this paper, we present a unifying regularization functional that depends on an operator L\documentclass[12pt]{ ...

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

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 ...

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

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 ...

A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is lost. For image da ...

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 ...

Achieving reactive robot behavior in complex dynamic environments is still challenging as it relies on being able to solve trajectory optimization problems quickly enough, such that we can replan the future motion at frequencies which are sufficiently high ...

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 ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...

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 ...

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 ...

Deep learning has achieved remarkable success in various challenging tasks such as generating images from natural language or engaging in lengthy conversations with humans. The success in practice stems from the ability to successfully train massive neural ...

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 ...

Universal Approximation Property of Hamiltonian Deep Neural Networks

Chat with Graph Search

Robust direct acoustic impedance control using two microphones for mixed feedforward-feedback controller

Effective annotation for the automatic vectorization of cadastral maps

Learning Activation Functions in Deep (Spline) Neural Networks

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

From Kernel Methods to Neural Networks: A Unifying Variational Formulation

The inductive bias of deep learning: Connecting weights and functions

An exact mapping from ReLU networks to spiking neural networks

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

Benign Overfitting in Deep Neural Networks under Lazy Training

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

How deep convolutional neural networks lose spatial information with training

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

VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behavior

Backpropagation-Friendly Eigendecomposition

Supervised learning and inference of spiking neural networks with temporal coding

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Combining Multiple Views for Visual Speech Recognition

Generalized Poisson Summation Formulas for Continuous Functions of Polynomial Growth

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

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