Learning Linearized Degradation of Health Indicators using Deep Koopman Operator Approach

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.

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Many applications, e.g. in content recommendation, sports, or recruitment, leverage the comparisons of alternatives to score those alternatives. The classical Bradley-Terry model and its variants have been widely used to do so. The historical model conside ...

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 ...

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

We study the problem of performance optimization of closed -loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated to be effective for improving closed -loop performance by automatically tuning controller gains or re ...

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 ...

Situational awareness strategies are essential for the reliable and secure operation of the electric power grid which represents critical infrastructure in modern society. With the rise of converter-interfaced renewable generation and the consequent shift ...

Dynamical system (DS) based motion planning offers collision-free motion, with closed-loop reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated by reshaping a nominal DS through matrix modulation, which is construc ...

Dexterous in-hand manipulation in robotics, particularly with multi-fingered robotic hands, poses significant challenges due to the intricate avoidance of collisions among fingers and the object being manipulated. Collision-free paths for all fingers must ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Daily manipulation tasks are characterized by regular features associated with the task structure, which can be described by multiple geometric primitives related to actions and object shapes. Only using Cartesian coordinate systems cannot fully represent ...

The current restrictions on the registration of combustion engines in different countries and the harmful impacts of fossil fuels on the environment and human health have motivated decision-makers to use batteries and/or fuel cells as alternatives for comb ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

Predictive health assessment is of vital importance for smarter battery management to ensure optimal and safe operations and thus make the most use of battery life. This paper proposes a general framework for battery aging prognostics in order to provide t ...

Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

Learning Linearized Degradation of Health Indicators using Deep Koopman Operator Approach

Chattez avec Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Generalized Bradley-Terry Models for Score Estimation from Paired Comparisons

Topics in statistical physics of high-dimensional machine learning

Navigating the Loop: From Control Systems to Neural Networks and Back

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Violation-aware contextual Bayesian optimization for controller performance optimization with unmodeled constraints

Understanding generalization and robustness in modern deep learning

Functional-Basis Analysis of Non-Stationary Signals in Modern Power Grids: Theory and Implementation in Embedded Systems

Reactive collision-free motion generation in joint space via dynamical systems and sampling-based MPC

Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multifingered In-Hand Manipulation

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

A geometric optimal control approach for imitation and generalization of manipulation skills

Electrochemical devices and computer science: water/thermal management of proton exchange membrane fuel cells and electrolyzers in different scales

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection

Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning