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

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.

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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

Chat with Graph Search

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

Efficient Continual Finite-Sum Minimization

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Simplification of spiking neural network models

Residual-based attention in physics-informed neural networks

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Topics in statistical physics of high-dimensional machine learning

Generalization of Scaled Deep ResNets in the Mean-Field Regime

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

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

Influence of Viscous Lubricant on Nucleation and Propagation of Frictional Ruptures

Permeability sets the linear path instability of buoyancy-driven disks

Measurement and modelling of dynamic fluid saturation in carbon reinforcements

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

On double-descent in uncertainty quantification in overparametrized models

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

Deep Learning Generalization with Limited and Noisy Labels

Predicting nonlinear optical scattering with physics-driven neural networks

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

Polynomial-time universality and limitations of deep learning