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.

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically different for narrow net-works, which tend to get stuck in badly-generalizing loca ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Applying hydrostatic pressure with suspended 2D material thin membranes allows probing the effects of lateral strain on the ion and fluid transport through nanopores. We demonstrate how both permanent and temporary delamination of 2D materials can be induc ...

The identification and segmentation of histological regions of interest can provide significant support to pathologists in their diagnostic tasks. However, segmentation methods are constrained by the difficulty in obtaining pixel-level annotations, which a ...

In this thesis, we advocate that Computer-Aided Engineering could benefit from a Geometric Deep Learning revolution, similarly to the way that Deep Learning revolutionized Computer Vision. To do so, we consider a variety of Computer-Aided Engineering pr ...

Laboratory three-point bending experiments are carried out to evaluate the effect of various fluids on the tensile strength of granite. The granite specimens were tested under both dry and saturated conditions. The fluids used to saturate the granite inclu ...

In this paper we explore deep learning models to monitor longitudinal liveability changes in Dutch cities at the neighbourhood level. Our liveability reference data is defined by a country-wise yearly survey based on a set of indicators combined into a liv ...

The dynamical properties of water molecules confinedin the unidirectionalhydrophilic nanopores of AlPO4-54 are investigated withquasi-elastic neutron scattering as a function of temperature downto 118 K. AlPO4-54 has among the largest pores known foralumin ...

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its success is still missing. This article presents, for orthogonal input vectors, ...

State-of-the-art object detection and segmentation methods for microscopy images rely on supervised machine learning, which requires laborious manual annotation of training data. Here we present a self-supervised method based on time arrow prediction pre-t ...

Neural Architecture Search (NAS) has fostered the automatic discovery of stateof- the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. In this work, we study the generaliza ...

In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...

Understanding the interaction between complicated geophysical flows and barriers remains a critical challenge for hazards countermeasures in engineering design. In this study, the impact of geophysical flows on a rigid barrier is studied numerically using ...

This work aims to study the effects of wind uncertainties in civil engineering structural design. Optimising the design of a structure for safety or operability without factoring in these uncertainties can result in a design that is not robust to these per ...

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

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

Chat with Graph Search

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Transformer Models for Vision

Stress induced delamination of suspended MoS2 in aqueous environments

Weakly supervised joint whole-slide segmentation and classification in prostate cancer

Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering

Weakening effect of various pore fluids on the tensile strength of granite

Time Series Analysis of Urban Liveability

Low-Temperature Dynamics of Water Confined in Unidirectional Hydrophilic Zeolite Nanopores

Probabilistic methods for neural combinatorial optimization

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Self-supervised Dense Representation Learning for Live-Cell Microscopy with Time Arrow Prediction

Generalization Properties of NAS under Activation and Skip Connection Search

Deep Learning for 3D Surface Modelling and Reconstruction

A new insight into the dynamic impact between geophysical flow and rigid barrier

Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation

Stable Nonconvex-Nonconcave Training via Linear Interpolation