Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

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.

Spectral algorithms are some of the main tools in optimization and inference problems on graphs. Typically, the graph is encoded as a matrix and eigenvectors and eigenvalues of the matrix are then used to solve the given graph problem. Spectral algorithms ...

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 ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Digital twins are virtual models of physical objects or systems that enable real-time monitoring and analysis. In the ﬁeld of stone masonry buildings, digital twins can be used to assess damage, predict maintenance needs, and opti- mize building performanc ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

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 ...

Much of our knowledge about the brain is derived from extracellular recordings of the electric fields produced by neural activity. However, interpretation of these signals is nontrivial. In par- ticular, it is difficult to link macro-scale observations of ...

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 ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

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 ...

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

In nature, most microbial populations have complex spatial structures that can affect their evolution. Evolutionary graph theory predicts that some spatial structures modelled by placing individuals on the nodes of a graph affect the probability that a mut ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Chattez avec Graph Search

The Power of Two Matrices in Spectral Algorithms for Community Recovery

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

Partial discharge localization in power transformer tanks using machine learning methods

Digital Twins of Stone Masonry Buildings for Damage Assessment

Robust machine learning for neuroscientific inference

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Understanding generalization and robustness in modern deep learning

Coupled Electromagnetic-Electrophysiological Modeling of Neural Circuits

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Aggregating Spatial and Photometric Context for Photometric Stereo

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Mutant fate in spatially structured populations on graphs: Connecting models to experiments

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Incorporating Projective Geometry into Deep Learning