Publications related to Foreword to the Special Issue on Machine Learning for Remote Sensing Data Processing

Related publications (27)

Comparison of Reservoir Computing topologies using the Recurrent Kernel approach

Reservoir Computing (RC) has become popular in recent years thanks to its fast and efficient computational capabilities. Standard RC has been shown to be equivalent in the asymptotic limit to Recurrent Kernels, which helps in analyzing its expressive power ...

2025

X-ray Micro-CT based characterization of rock cuttings with deep learning

Nils Frédérik Heiden Olsen, Alexandre Massoud Alahi, Pascal Turberg

Rock cuttings from destructive boreholes are a common and cheaper source of drilling materials that can be used to determine underground geology compared to rock core samples. Classifying manually the series of cuttings can be a long and tedious process an ...

2025

Learning Unitaries with Quantum Statistical Queries

Armando Angrisani

We propose several algorithms for learning unitary operators from quantum statistical queries with respect to their Choi-Jamiolkowski state. Quantum statistical queries capture the capabilities of a learner with limited quantum resources, which receives as ...

VEREIN FORDERUNG OPEN ACCESS PUBLIZIERENS QUANTENWISSENSCHAF2025

A coordinate transformation-based physics-informed neural networks for hyperbolic conservation laws

Jan Sickmann Hesthaven

Hyperbolic conservation laws play a critical role in various fields, including aerodynamics, physics, and oceanography. However, traditional physics-informed neural networks (PINNs), despite their remarkable capabilities in solving partial differential equ ...

2025

Les Houches lectures on deep learning at large and infinite width

Vittorio Erba, Christian Keup

These lectures, presented at the 2022 Les Houches Summer School on Statistical Physics and Machine Learning, focus on the infinite-width limit and large-width regime of deep neural networks. Topics covered include the various statistical and dynamical prop ...

2024

IM-Context: In-Context Learning for Imbalanced Regression Tasks

Olga Fink, Ismail Nejjar

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in underrepresented regio ...

Neural information processing systems foundation2024

Machine-Learning-Enhanced Procedural Modeling for 4D Historical Cities Reconstruction

Frédéric Kaplan, Isabella Di Lenardo, Rémi Guillaume Petitpierre, Beatrice Vaienti

The generation of 3D models depicting cities in the past holds great potential for documentation and educational purposes. However, it is often hindered by incomplete historical data and the specialized expertise required. To address these challenges, we p ...

2023

Artificial intelligence and visual analytics in geographical space and cyberspace: Research opportunities and challenges

Stéphane Joost, François Golay

In recent decades, we have witnessed great advances on the Internet of Things, mobile devices, sensor-based systems, and resulting big data infrastructures, which have gradually, yet fundamentally influenced the way people interact with and in the digital ...

ELSEVIER2023

The inductive bias of deep learning: Connecting weights and functions

Guillermo Ortiz Jimenez

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

EPFL2023

Interpretable Inflammation Landscape of Circulating Immune cells

Francesco Craighero

Inflammation is a biological phenomenon involved in a wide variety of physiological and pathological processes. Although a controlled inflammatory response is beneficial for restoring homeostasis, it can become unfavorable if dysregulated. In recent years, ...

2023

On the advantages of P2P ML on mobile devices

Rachid Guerraoui, Alexandre David Olivier Maurer

Many fields make use nowadays of machine learning (ML) enhanced applications for cost optimization, scheduling or forecasting, in- cluding the energy sector. However, these very ML algorithms consume a significant amount of energy, sometimes going against ...

ACM2022

Large deviations of semisupervised learning in the stochastic block model

Lenka Zdeborová, Hugo Chao Cui, Luca Saglietti

In semisupervised community detection, the membership of a set of revealed nodes is known in addition to the graph structure and can be leveraged to achieve better inference accuracies. While previous works investigated the case where the revealed nodes ar ...

AMER PHYSICAL SOC2022

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

Volkan Cevher, Fanghui Liu, Luca Viano

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

2022

Local Kernel Regression and Neural Network Approaches to the Conformational Landscapes of Oligopeptides

Michele Ceriotti, Anne-Clémence Corminboeuf, Alberto Fabrizio, Benjamin André René Meyer, Raimon Fabregat I De Aguilar-Amat, Edgar Albert Engel, Veronika Juraskova

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been pr ...

2022

Role of the androgen receptor in the human breast epithelium

Fabio De Martino

Breast cancer is the most common malignancy in women worldwide and understanding the risk factors affecting it is key for prevention. The relative risk of developing breast cancer is related to exposure to both endogenous hormones and exogenous natural and ...

EPFL2022

SPAHM: the spectrum of approximated Hamiltonian matrices representations

Anne-Clémence Corminboeuf, Alberto Fabrizio, Ksenia Briling

Physics-inspired molecular representations are the cornerstone of similarity-based learning applied to solve chemical problems. Despite their conceptual and mathematical diversity, this class of descriptors shares a common underlying philosophy: they all r ...

2022

Hardware-oriented pruning and quantization of Deep Learning models to detect life-threatening arrhythmias

Alexandre Schmid

Wearable solutions based on Deep Learning (DL) for real-time ECG monitoring are a promising alternative to detect life-threatening arrhythmias. However, DL models suffer of a large memory footprint, which hampers their adoption in portable technologies. Th ...

IEEE2021

On Maintaining Linear Convergence of Distributed Learning and Optimization Under Limited Communication

Na Li

In distributed optimization and machine learning, multiple nodes coordinate to solve large problems. To do this, the nodes need to compress important algorithm information to bits so that it can be communicated over a digital channel. The communication tim ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Second-Order Guarantees In Federated Learning

Ali H. Sayed, Stefan Vlaski, Elsa Rizk

Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep learning settings, which generally giv ...

IEEE2020

Towards Scalable Personalization

Rhicheek Patra

The ever-growing amount of online information calls for Personalization. Among the various personalization systems, recommenders have become increasingly popular in recent years. Recommenders typically use collaborative filtering to suggest the most releva ...

EPFL2018