Adaptive data augmentation for image classification

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

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 ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

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 ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

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 ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

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 ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

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 ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Adaptive data augmentation for image classification

Chattez avec Graph Search

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Topics in statistical physics of high-dimensional machine learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

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

Random matrix methods for high-dimensional machine learning models

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Aggregating Spatial and Photometric Context for Photometric Stereo

Understanding generalization and robustness in modern deep learning

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Safe Deep Neural Networks

Enabling Uncertainty Estimation in Iterative Neural Networks

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Machine Learning for Modeling Stock Returns

Robust NAS under adversarial training: benchmark, theory, and beyond

Sparse autoregressive neural networks for classical spin systems

On the number of regions of piecewise linear neural networks

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs