Publications associées à Shape optimisation of technical devices via gradient descent using convolutional neural network proxies

Publications associées (36)

Characterization of Machine Learning-Based Surrogate Models of Neural Activation Under Electrical Stimulation

Bioelectromagnetics published by Wiley Periodicals LLC on behalf of Bioelectromagnetics Society.Electrical stimulation of peripheral nerves via implanted electrodes has been shown to be a promising approach to restore sensation, movement, and autonomic fun ...

2025

Efficient Continual Finite-Sum Minimization

Ioannis Mavrothalassitis, Volkan Cevher, Leello Tadesse Dadi, Efstratios Panteleimon Skoulakis

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Simplification of spiking neural network models

Wulfram Gerstner, Henry Markram, Eilif Benjamin Muller, James Gonzalo King, Christian Antonio Pozzorini, Csaba Erö, Christian Andreas Rössert, Idan Segev, Willem Anna Mark Wybo

The simplification of neural network models is described. For example, a method for simplifying a neural network model includes providing the neural network model to be simplified, defining a first temporal filter for the conveyance of input from a neuron ...

2024

Residual-based attention in physics-informed neural networks

Nikolaos Stergiopoulos, Sokratis Anagnostopoulos

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Elsevier Science Sa2024

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Scott William Pesme, Hristo Georgiev Papazov

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

EPFL2023

Visualization and modelling of dynamic flow in fibrous preforms for liquid composite molding

Helena Luisa Teixido Pedarros

Nowadays, Liquid Composite Molding techniques are often used to manufacture high quality fiber reinforced composite parts at a relatively low cost. These involve an infiltration process, in which a liquid resin is forced to ingress into a dry fibrous porou ...

EPFL2023

Influence of Viscous Lubricant on Nucleation and Propagation of Frictional Ruptures

Marie Estelle Solange Violay, François Xavier Thibault Passelègue, Federica Paglialunga

Fluids are pervasive in the Earth's crust and saturate fractures and faults. The combination of fluids and gouge layers developing along faults can generate fluids of different viscosities. Such viscous fluids were found to influence the reactivation, fric ...

2023

Permeability sets the linear path instability of buoyancy-driven disks

François Gallaire, Pier Giuseppe Ledda, Giuseppe Antonio Zampogna

The prediction of trajectories of buoyancy-driven objects immersed in a viscous fluid is a key problem in fluid dynamics. Simple-shaped objects, such as disks, present a great variety of trajectories, ranging from zig-zag to tumbling and chaotic motions. Y ...

Cambridge University Press2023

Measurement and modelling of dynamic fluid saturation in carbon reinforcements

Véronique Michaud, Baris Çaglar, Guillaume Clément Broggi, Helena Luisa Teixido Pedarros

We propose a methodology to monitor the progressive saturation of a non-translucent unidirectional carbon fabric stack through its thickness by means of X-ray radiography and extract the dynamic saturation curves using image analysis. Four constant flow ra ...

2023

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Giancarlo Ferrari Trecate, Luca Furieri, Liang Xu, Clara Lucía Galimberti

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 ...

2023

On double-descent in uncertainty quantification in overparametrized models

Lenka Zdeborová, Florent Gérard Krzakala, Bruno Loureiro, Lucas Andry Clarte

Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estimates in the context of overparametrized neural networks. Several methods, ra ...

PMLR Proceedings of Machine Learning Research2023

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods

Michaël Unser, Pakshal Narendra Bohra, Pol del Aguila Pla

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

2023

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

Predicting nonlinear optical scattering with physics-driven neural networks

Demetri Psaltis, Carlo Gigli

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

AIP Publishing2023

Reduced order modeling of parametrized pulsatile blood flows: Hematocrit percentage and heart rate

Ricardo Reyes Sotomayor

This paper numerically evaluates the accuracy and performance of a stabilized finite element Reduced Order Modelling (ROM) approach that is designed to simulate pulsatile blood flows. The method is able to estimate fluid flow parametric solutions of intere ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Polynomial-time universality and limitations of deep learning

Emmanuel Abbé

The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...

WILEY2023