1 code implementation • 20 Nov 2023 • Hao Dong, Gaëtan Frusque, Yue Zhao, Eleni Chatzi, Olga Fink
While AD is typically treated as an unsupervised learning task due to the high cost of label annotation, it is more practical to assume access to a small set of labeled anomaly samples from domain experts, as is the case for semi-supervised anomaly detection.
no code implementations • 31 Oct 2023 • Marcus Haywood-Alexander, Wei Liu, Kiran Bacsa, Zhilu Lai, Eleni Chatzi
The intersection of physics and machine learning has given rise to the physics-enhanced machine learning (PEML) paradigm, aiming to improve the capabilities and reduce the individual shortcomings of data- or physics-only methods.
1 code implementation • NeurIPS 2023 • Hao Dong, Ismail Nejjar, Han Sun, Eleni Chatzi, Olga Fink
In real-world scenarios, achieving domain generalization (DG) presents significant challenges as models are required to generalize to unknown target distributions.
no code implementations • 1 Oct 2023 • Yuriy Marykovskiy, Thomas Clark, Justin Day, Marcus Wiens, Charles Henderson, Julian Quick, Imad Abdallah, Anna Maria Sempreviva, Jean-Paul Calbimonte, Eleni Chatzi, Sarah Barber
It presents the main concepts underpinning Knowledge-Based Systems and summarises previous work in the areas of knowledge engineering and knowledge representation in a manner that is relevant and accessible to domain experts.
1 code implementation • 16 Jul 2023 • Giacomo Arcieri, Cyprien Hoelzl, Oliver Schwery, Daniel Straub, Konstantinos G. Papakonstantinou, Eleni Chatzi
The POMDP with uncertain parameters is then solved via deep RL techniques with the parameter distributions incorporated into the solution via domain randomization, in order to develop solutions that are robust to model uncertainty.
1 code implementation • 15 Dec 2022 • Giacomo Arcieri, Cyprien Hoelzl, Oliver Schwery, Daniel Straub, Konstantinos G. Papakonstantinou, Eleni Chatzi
We present a framework to estimate POMDP transition and observation model parameters directly from available data, via Markov Chain Monte Carlo (MCMC) sampling of a Hidden Markov Model (HMM) conditioned on actions.
1 code implementation • 9 Oct 2022 • Wei Liu, Zhilu Lai, Kiran Bacsa, Eleni Chatzi
Typically, conventional variational inference models are parameterized by neural networks independent of the latent dynamics models.
no code implementations • 26 Sep 2022 • Cyprien Amadis Hoelzl, Vasilis Dertimanis, Lucian Ancu, Aurelia Kollros, Eleni Chatzi
Intelligent data-driven monitoring procedures hold enormous potential for ensuring safe operation and optimal management of the railway infrastructure in the face of increasing demands on cost and efficiency.
1 code implementation • 16 Jul 2022 • Zhilu Lai, Wei Liu, Xudong Jian, Kiran Bacsa, Limin Sun, Eleni Chatzi
In the scope of physics-informed machine learning, this paper proposes a framework -- termed Neural Modal ODEs -- to integrate physics-based modeling with deep learning for modeling the dynamics of monitored and high-dimensional engineered systems.
1 code implementation • 25 Oct 2021 • Giacomo Arcieri, David Wölfle, Eleni Chatzi
The main contribution of this work lies precisely in assessing the model influence on the performance of RL algorithms.
1 code implementation • 16 Oct 2021 • Wei Liu, Zhilu Lai, Kiran Bacsa, Eleni Chatzi
To address this, we bridge physics-based state space models with Deep Markov Models, thus delivering a hybrid modeling framework for unsupervised learning and identification of nonlinear dynamical systems.
no code implementations • NeurIPS 2021 • Charilaos Mylonas, Imad Abdallah, Eleni Chatzi
Graph Networks (GNs) enable the fusion of prior knowledge and relational reasoning with flexible function approximations.
no code implementations • 12 Mar 2021 • Antonios Kamariotis, Eleni Chatzi, Daniel Straub
We quantify this value by adaptation of the Bayesian decision analysis framework.
Applications Systems and Control Systems and Control
no code implementations • 5 Mar 2021 • George Tsialiamanis, Charilaos Mylonas, Eleni Chatzi, Nikolaos Dervilis, David J. Wagg, Keith Worden
One of the requirements of the population-based approach to Structural Health Monitoring (SHM) proposed in the earlier papers in this sequence, is that structures be represented by points in an abstract space.
1 code implementation • 23 Nov 2020 • Charilaos Mylonas, Eleni Chatzi
In this work, a novel approach for the construction and training of time series models is presented that deals with the problem of learning on large time series with non-equispaced observations, which at the same time may possess features of interest that span multiple scales.