Publications associées à Gradient free cooperative seeking of a moving source

Publications associées (22)

OPTIMAL TRANSPORT-INSPIRED DEEP LEARNING FRAMEWORK FOR SLOW-DECAYING KOLMOGOROV \bfitn-WIDTH PROBLEMS: EXPLOITING SINKHORN LOSS AND WASSERSTEIN KERNEL

Reduced-order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems. However, traditional ROM methods may only partially capture the intrinsic geometric characteristics of the data. These characteristics encompass the und ...

2025

Gradient Approximation of Approximate Multipliers for High-Accuracy Deep Neural Network Retraining

Giovanni De Micheli, Chang Meng

Approximate multipliers (AppMults) are widely employed in deep neural network (DNN) accelerators to reduce the area, delay, and power consumption. However, the inaccuracies of AppMults degrade DNN accuracy, necessitating a retraining process to recover acc ...

Institute of Electrical and Electronics Engineers2025

High-dimensional learning of narrow neural networks

Hugo Chao Cui

Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning (ML) applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks (NNs) to learn from high-dimensional data ...

2025

A Large Deviations Perspective on Policy Gradient Algorithms

Mengmeng Li, Daniel Kuhn, Wouter Jongeneel

Motivated by policy gradient methods in the context of reinforcement learning, we derive the first large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a Polyak-Łojasiewicz co ...

2024

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Michaël Unser, Dimitris Perdios, Alexis Marie Frederic Goujon, Pakshal Narendra Bohra, Sebastian Jonas Neumayer, Stanislas Ducotterd

Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both theoretically and empi ...

2024

High-Permittivity Polysiloxanes for Bright, Stretchable Electroluminescent Devices

Frank Nüesch, Wei-Hsu Hu

Stretchable alternating current electroluminescent (ACEL) devices have a bright future in wearable electronics and soft robotics. Still, their market application is hindered by high operating voltages. The voltage can be reduced by increasing the relative ...

Wiley-V C H Verlag Gmbh2024

Predicting electronic screening for fast Koopmans spectral functional calculations

Nicola Marzari

Koopmans spectral functionals are a powerful extension of Kohn-Sham density-functional theory (DFT) that enables the prediction of spectral properties with state-of-the-art accuracy. The success of these functionals relies on capturing the effects of elect ...

2024

Wigner kernels: Body-ordered equivariant machine learning without a basis

Michele Ceriotti, Sergey Pozdnyakov, Filippo Bigi

Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that h ...

AIP Publishing2024

ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations

Devis Tuia, Antoine Bosselut, Javiera Francisca Castillo Navarro, Syrielle Mathilde Marie Montariol, Li Mi

Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientat ...

Springer Cham2024

Tower-foot grounding model for EMT programs based on transmission line theory and Marti's model

Rafael Silva Alipio

This paper proposes a tower-foot grounding system model compatible with EMT programs which might be useful for the simulation of lightning transients in overhead lines. The proposed model is based on the solution of the telegrapher's equations and the appl ...

Elsevier2023

Two-layer adaptive signal control framework for large-scale dynamically-congested networks: Combining efficient Max Pressure with Perimeter Control

Nikolaos Geroliminis, Dimitrios Tsitsokas

Traffic-responsive signal control is a cost-effective, easy-to-implement, network management strategy, bearing high potential to improve performance in heavily congested networks with dy-namic traffic characteristics. Max Pressure (MP) distributed control ...

PERGAMON-ELSEVIER SCIENCE LTD2023

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Sabine Süsstrunk, Radhakrishna Achanta, Mahmut Sami Arpa, Martin Nicolas Everaert

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

BMVA2023

Current and friction transients during tribocorrosion of a biomedical titanium alloy sliding against zirconia

Stefano Mischler, Anna Neus Igual Muñoz, Anna Dalmau Mallorquí

The tribocorrosion mechanisms of a Ti-Nb-Zr-Ta (TNZT) alloy rubbing against a zirconia ball in a Phosphate Buffered Solution (PBS) were analyzed by considering the mechanical and chemical interactions that lead to the material degradation. To understand th ...

ELSEVIER SCIENCE SA2023

Jacobian-free variational method for computing connecting orbits in nonlinear dynamical systems

Tobias Schneider, Omid Ashtari

One approach for describing spatiotemporal chaos is to study the unstable invariant sets embedded in the chaotic attractor of the system. While equilibria, periodic orbits, and invariant tori can be computed using existing methods, the numerical identifica ...

American Institute of Physics2023

Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems

David Atienza Alonso, Amir Aminifar, Tomas Teijeiro Campo, Saleh Baghersalimi

In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains ...

2023

Multi-agent reinforcement learning with graph convolutional neural networks for optimal bidding strategies of generation units in electricity markets

Olga Fink

Finding optimal bidding strategies for generation units in electricity markets would result in higher profit. However, it is a challenging problem due to the system uncertainty which is due to the lack of knowledge of the strategies of other generation uni ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition

Tao Lin

In wearable-based human activity recognition (HAR) research, one of the major challenges is the large intra-class variability problem. The collected activity signal is often, if not always, coupled with noises or bias caused by personal, environmental, or ...

ASSOC COMPUTING MACHINERY2022

A machine learning-driven two-phase metaheuristic for autonomous ridesharing operations

Nikolaos Geroliminis, Claudia Bongiovanni

This paper contributes to the intersection of operations research and machine learning in the context of autonomous ridesharing. In this work, autonomous ridesharing operations are reproduced through an event-based simulation approach and are modeled as a ...

PERGAMON-ELSEVIER SCIENCE LTD2022

Simultaneous Prediction of Wrist and Hand Motions via Wearable Ultrasound Sensing for Natural Control of Hand Prostheses

Xingchen Yang

Simultaneous prediction of wrist and hand motions is essential for the natural interaction with hand prostheses. In this paper, we propose a novel multi-out Gaussian process (MOGP) model and a multi-task deep learning (MTDL) algorithm to achieve simultaneo ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning

Anne-Marie Kermarrec, Erick Lavoie

The convergence speed of machine learning models trained with Federated Learning is significantly affected by non-independent and identically distributed (non-IID) data partitions, even more so in a fully decentralized setting without a central server. In ...

2022