Publications associées à Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods

Publications associées (19)

Reverse engineering primate sensorimotor control with machine learning

The ability of the brain to produce adaptive and dexterous movements relies on the seamless integration of sensory feedback into motor commands. Despite significant advances in motor neuroscience, critical gaps persist in understanding how proprioceptive a ...

EPFL2025

Mathematical Analysis and Optimization of Features for Atomistic Machine Learning

Kevin Kazuki Huguenin-Dumittan

Computational methods at the atomic scale based on machine learning have been a fruitful research field in the past decade by merging the advantages of classical and quantum mechanical approaches. While parts of the field are already reaching a mature stat ...

EPFL2025

Universality laws for Gaussian mixtures in generalized linear models

Lenka Zdeborová, Florent Gérard Krzakala, Bruno Loureiro, Ludovic Théo Stephan, Yatin Dandi

A recent line of work in high-dimensional statistics working under the Gaussian mixture hypothesis has led to a number of results in the context of empirical risk minimization, Bayesian uncertainty quantification, separation of kernel methods and neural ne ...

2024

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Wenlong Liao

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

2024

Uncertainty quantification in groundwater volume predictions from seismic data using neural networks

Jan Sickmann Hesthaven

Optimum groundwater management is important for addressing the global challenges of water scarcity, especially in arid regions. This study demonstrates the application of synthetic data combined with seismic methods to quantify water volumes in a controlle ...

European Association of Geoscientists and Engineers, EAGE2024

Learning Time-Scales in Two-Layers Neural Networks

Raphaël Jean Berthier

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progre ...

2024

Neurostimulation and Wireless Data Transmission Circuits for Implantable High-Density Neural Interfaces

Cong Ding

Over the past years, implantable closed-loop neural interfaces have received increasing attention for their potential to enhance the understanding of the brain, treat neurological disorders, and provide unprecedented opportunities for individuals with para ...

EPFL2024

Partial annotations in active learning for semantic segmentation

Katrin Beyer, Radhakrishna Achanta

Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning model ...

2024

Reduced order models to address temporal complexity and geometrical variability in hemodynamics

Riccardo Tenderini

In recent years, numerical simulations of hemodynamics have gained significant attention within the medical community, thanks to their ability of non-invasively estimating the blood flow conditions. However, high-fidelity simulations require extensive comp ...

EPFL2024

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Tanja Christina Käser Jacober, Vinitra Swamy, Jibril Albachir Frej

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

2023

The statistical complexity of early-stopped mirror descent

Tomas Vaskevicius

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

Oxford University Press2023

Constrained Form-Finding of Tension-Compression Structures using Automatic Differentiation

Stefana Parascho

This paper proposes a computational approach to form-find pin-jointed bar structures subjected to combinations of tension and compression forces. The generated equilibrium states can meet structural and geometrical constraints via gradient-based optimizati ...

ELSEVIER SCI LTD2023

Bayes-optimal inference for spreading processes on random networks

Lenka Zdeborová, Davide Ghio, Indaco Biazzo

We consider a class of spreading processes on networks, which generalize commonly used epidemic models such as the SIR model or the SIS model with a bounded number of reinfections. We analyze the related problem of inference of the dynamics based on its pa ...

Amer Physical Soc2023

Teaching machines how to find strongly lensed galaxies in cosmological sky surveys

Elodie Marie Charlène Savary

Analyzing gravitationally lensed objects enables a wide range of physical and cosmological applications, such as probing the dark matter content in galaxies and clusters or measuring the Universe's expansion rate. The precision of these applications can be ...

EPFL2022

Event-driven acquisition for content-enriched microscopy

Suliana Manley, Dora Mahecic, Martin Weigert, Juliette Griffie, Chen Zhang, Willi Leopold Stepp

Event-driven acquisition uses neural-network-based recognition of specific biological events to trigger switching between slow and fast super-resolution imaging, enriching the capture of interesting events with high spatiotemporal resolution. A common goal ...

Nature Publishing Group2022

A Wearable Smart Glove and Its Application of Pose and Gesture Detection to Sign Language Classification

Josephine Anna Eleanor Hughes

Advances in soft sensors coupled with machine learning are enabling increasingly capable wearable systems. Since hand motion in particular can convey useful information for developing intuitive interfaces, glove-based systems can have a significant impact ...

Institute of Electrical and Electronics Engineers Inc.2022

Complex Analysis meets Statistical Mechanics: Applications to Kernel Methods and Conformal Field Theory

Francesco Spadaro

This thesis is centered on questions coming from Machine Learning (ML) and Statistical Field Theory (SFT). In Machine Learning, we consider the subfield of Supervised Learning (SL), and in particular regression tasks where one tries to find a regressor tha ...

EPFL2021

A Flexible In-Memory Computing Architecture for Heterogeneously Quantized CNNs

David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Flavio Ponzina, Marco Antonio Rios

Inferences using Convolutional Neural Networks (CNNs) are resource and energy intensive. Therefore, their execution on highly constrained edge devices demands the careful co-optimization of algorithms and hardware. Addressing this challenge, in this paper ...

2021

LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions

Oguz Kaan Yüksel

Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing op ...

IEEE2021