Publications associées à Universal Approximation Property of Hamiltonian Deep Neural Networks

Publications associées (43)

Programming Light Propagation for Efficient Artificial Intelligence

Contemporary artificial intelligence (AI) models' exponentially growing complexity translates to their expanding skill sets. They can create language or image content mimicking human creativity and understanding, becoming indispensable tools in education, ...

EPFL2025

Bayes-optimal learning of deep random networks of extensive-width*

Lenka Zdeborová, Florent Gérard Krzakala, Hugo Chao Cui

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

IOP Publishing Ltd2025

LIU-NET: lightweight Inception U-Net for efficient brain tumor segmentation from multimodal 3D MRI images

Zaffar Ahmed Shaikh

Segmenting brain tumors is a critical task in medical imaging that relies on advanced deep-learning methods. However, effectively handling complex tumor regions requires more comprehensive and advanced strategies to overcome challenges such as computationa ...

2025

Data-driven dynamic friction models based on Recurrent Neural Networks

Gaëtan Bixente Cortes, Antonio Joaquin Garcia Suarez

In this concise contribution, it is demonstrated that Recurrent Neural Networks (RNNs) based on Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction (RSF) laws from synthetic data. The dat ...

2025

Scaling the Modalities in Multimodal Foundation Models

Oguzhan Fatih Kar

Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...

EPFL2025

Optical Processors for AI Computing and Networking

Mustafa Yildirim

Computing has long been central to technological advancements, where each leap in compute power has catalyzed applications once thought impossible, such as smartphones. Recently, the exponential growth in the compute demand of artificial intelligence (AI) ...

EPFL2025

Inherent Structural Descriptors Via Machine Learning

Antonio Tinti

Finding proper collective variables for complex systems and processes is one of the most challenging tasks in simulations, which limits the interpretation of experimental and simulated data and the application of enhanced sampling techniques. Here, we prop ...

IOP Publishing Ltd2025

From Preprocessing to Evaluation: The Role of External Knowledge in Advancing Language Models and Machine Translation

Georgios Vernikos

Machine translation (MT) systems and language models (LMs) have demonstrated impressive performance in recent years, driven by advances in architecture, algorithms, and the scaling of parameters and training data. Despite the ability of these models to int ...

EPFL2025

Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images

Georg Fantner, Marcos Penedo Garcia

In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified r ...

Beilstein Institut2025

Towards Integrated Processing of Physiological Signals and Speech

Zohreh Mostaani

Research in speech processing has largely focused on source-system modeling, where vocal fold vibrations serve as the source and the vocal cavity's articulations as the system. Nonetheless, speech production includes a complex combination of physiological ...

EPFL2025

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu, Yongtao Wu

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

2022

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

Volkan Cevher, Fanghui Liu, Luca Viano

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

2022

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

Michaël Unser, Sebastian Jonas Neumayer, Lénaïc Chizat

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

2024

Theory of Deep Learning: Neural Tangent Kernel and Beyond

Arthur Ulysse Jacot-Guillarmod

In the recent years, Deep Neural Networks (DNNs) have managed to succeed at tasks that previously appeared impossible, such as human-level object recognition, text synthesis, translation, playing games and many more. In spite of these major achievements, o ...

EPFL2022

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Maude Girardin, Marco Picasso, Alexandre Caboussat

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Elsevier Science Sa2024

On the number of regions of piecewise linear neural networks

Michaël Unser, Alexis Marie Frederic Goujon

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

2024

Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach

Giancarlo Ferrari Trecate, Luca Furieri, Muhammad Zakwan, Clara Lucía Galimberti

Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly intrac ...

2022

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Sabine Süsstrunk, Mathieu Salzmann, Tao Lin, Chen Liu

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...

2021

De novo protein design by inversion of the AlphaFold structure prediction network

Benedict Dieter Gregor Wolf, Bruno Emanuel Ferreira De Sousa Correia, Stéphane Rosset, Casper Alexander Goverde, Hamed Khakzad

De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in comp ...

2023

ESSOP: Efficient and Scalable Stochastic Outer Product Architecture for Deep Learning

Irem Boybat Kara, Abu Sebastian

Deep neural networks (DNNs) have surpassed human-level accuracy in a variety of cognitive tasks but at the cost of significant memory/time requirements in DNN training. This limits their deployment in energy and memory limited applications that require rea ...

IEEE2020