A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
[article]
2022
arXiv
pre-print
Preserved Fulltext
Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. ...
The fault maps are then employed for fault-aware mapping and (if required) fault-aware re-training of DNNs. ...
DNN Post-fabrication Testing Fault Map Hardware Pre-Trained DNN Dataset Fault-Aware Masking of DNN Fault-Aware Re-Training (Repeat for Every Mini-batch) Loss and Gradient Computation Weight Update Fault-Aware ...
arXiv:2204.09514v1
fatcat:ho7auszvmferrn36evs7oqdpt4
On-line anomaly detection and resilience in classifier ensembles
2013
Pattern Recognition Letters
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Detection of anomalies is a broad field of study, which is applied in different areas such as data monitoring, navigation, and pattern recognition. ...
Upon detection of anomalous classifiers we propose a strategy that attempts to minimize adverse effects of faulty classifiers by excluding them from the ensemble. ...
On-line anomaly detection and resilience in classifier ensembles. ...
doi:10.1016/j.patrec.2013.02.014
fatcat:gp4lhipuindqrhvandxmuefgny
Data‐driven operation of the resilient electric grid: A case of COVID‐19
2021
The Journal of Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
These data or information can be employed to take advantage of advanced machine learning techniques for automation and increased power grid resilience. ...
emergency planning and organisational support, (b) following safety protocol, (c) utilising enhanced automation and sensing for situational awareness, and (d) integration of advanced technologies and data ...
Real-time event detection using synchrophasor data, and ensemble methodology that includes maximum likelihood estimation, DBSCAN, and decision trees. [55] Fault section estimation. ...
doi:10.1049/tje2.12065
pmid:34540233
pmcid:PMC8441621
fatcat:oglioz6qdraobb2jhuztrf24ra
Cyber-Physical Microgrids: Toward Future Resilient Communities
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper provides an overview of current research in microgrid resilience and presents an outlook for future trends. ...
Advanced monitoring and control are critical for real-time operations of microgrids and, therefore, directly influence communities' resilience. ...
Physics-based methods build indicators of faults, attacks, and anomalies using data related to the physical power network [62] . Physical data received from sensors are processed using the SE tools. ...
arXiv:1912.05682v1
fatcat:nqmvi2rpmreate75cbrhm7bdtu
Data-driven Operation of the Resilient Electric Grid: A Case of COVID-19
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
These data or information can be utilized to take advantage of advanced machine learning techniques for automation and increased power grid resilience. ...
a) emergency planning and organizational support, b) following safety protocol, c) utilizing enhanced automation and sensing for situational awareness, and d) integration of advanced technologies and data ...
Real-time event detection using synchrophasor data, and ensemble methodology that includes maximum likelihood estimation, DBSCAN, and decision trees. [53] Fault section estimation. ...
arXiv:2010.01746v3
fatcat:xdiohcjksjcqvc5who6atdldvu
Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects
2019
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We start by examining various proposed cloud/fog/edge architectures, highlighting their importance for acquiring manufacturing data in order to train the ML algorithms. ...
Towards this end, a detailed overview of ML-based human–machine interaction techniques is provided, allowing humans to be in-the-loop of the manufacturing processes in a symbiotic manner with minimal errors ...
new threats, and resilient against zero-day attacks. ...
doi:10.3390/s20010109
pmid:31878065
pmcid:PMC6983262
fatcat:n4muoguq5jalrfwqkq4264vswe
Byzantine Fault Tolerance in Distributed Machine Learning : a Survey
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Byzantine Fault Tolerance (BFT) is one of the most challenging problems in Distributed Machine Learning (DML), defined as the resilience of a fault-tolerant system in the presence of malicious components ...
Byzantine failures are still difficult to deal with due to their unrestricted nature, which results in the possibility of generating arbitrary data. ...
Momentum reduces gradient variation at the server and reinforces Byzantine resilient aggregation rules. Mirror Descent is used to secure training data against faulty information sharing. ...
arXiv:2205.02572v2
fatcat:b7dwh5ajnjazpkwfsvsfoioe5u
A Survey on Distributed Machine Learning
2020
ACM Computing Surveys
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To make these types of datasets accessible as training data for machine learning problems, algorithms have to be chosen and implemented that enable parallel computation, data distribution, and resilience ...
In some cases, the long runtime of training the models steers solution designers towards using distributed systems for an increase of parallelization and total amount of I/O bandwidth, as the training ...
Various different ways exist to perform ensembling, such as [50] : • Bagging is the process of building multiple classifiers and combining them into one. • Boosting is the process of training new models ...
doi:10.1145/3377454
fatcat:apwpdtza4zc2tcn37hnxxrb74u
Machine Learning Robustness: A Primer
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2024 pre-print arXiv:2404.00897v1 fatcat:huxovm6t2velvizdxwpvs3ckfuOther Versions
Lastly, post-training methods are discussed, including ensemble techniques, pruning, and model repairs, emerging as cost-effective strategies to make models more resilient against the unpredictable. ...
It covers non-adversarial data shifts and nuances of Deep Learning (DL) software testing methodologies. ...
[141] take another step, by training each model of an ensemble to be resilient to a different adversarial attack by injecting a small subset of adversarial examples, which profit to the ensemble globally ...
arXiv:2404.00897v3
fatcat:ag7ugiul4bd3pmznpdbd2ql74u
A Survey on Distributed Machine Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Although small machine learning models can be trained with modest amounts of data, the input for training larger models such as neural networks grows exponentially with the number of parameters. ...
However, in order to increase the quality of predictions and render machine learning solutions feasible for more complex applications, a substantial amount of training data is required. ...
Various dierent ways exist to perform ensembling, such as [50] : • Bagging is the process of building multiple classiers and combining them into one. • Boosting is the process of training new models with ...
arXiv:1912.09789v1
fatcat:kbjkeznysjaqtndgdubm52fxay
In-Network Sensor Data Modelling Methods for Fault Detection
[chapter]
2013
Communications in Computer and Information Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
To improve the data reliability, many sensor fault detection techniques have been proposed. ...
In this paper, we firstly discuss sensor data features and their relevance to fault detection. ...
the training data is error free. ...
doi:10.1007/978-3-319-04406-4_17
fatcat:ncsusej6rfbbnic37cug2mrrnu
Error motion trajectory-driven diagnostics of kinematic and non-kinematic machine tool faults
2022
Mechanical systems and signal processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Ensemble methods are investigated and shown to improve the generalisation ability when predicting on experimental data. ...
This paper presents a general approach to identifying both kinematic and non-kinematic faults in error motion trajectory data, by framing the issue as a generic pattern recognition problem. ...
Simulating fault-states in error motion trajectory data The ability to generate informative training data artificially is imperative to building an automated diagnostic system in this domain. ...
doi:10.1016/j.ymssp.2021.108271
fatcat:a2hsyap7crdpfgscielgbs5kbq
Resilience and fault tolerance in high-performance computing for numerical weather and climate prediction
2021
The international journal of high performance computing applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The potential impact of these strategies is discussed in relation to current development of numerical weather prediction algorithms and systems towards the exascale. ...
Numerical examples showcase the performance of the techniques in addressing faults, with particular emphasis on iterative solvers for linear systems, a staple of atmospheric fluid flow solvers. ...
While local memory-based approaches provide excellent performance for application faults, they fail to provide resilience against more serious hardware failures. ...
doi:10.1177/1094342021990433
fatcat:tfhovb6xmfemtkgzzrkpiiiju4
Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS
2020
IEEE Communications Surveys and Tutorials
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2102.07244v1 fatcat:xxfpnrnmtncktptkegaf7wju2q
One of the dominant methodologies explored for building resilient CPS is dependent on machine learning (ML) algorithms. ...
This paper is therefore aimed at comprehensively surveying the interactions between resilient CPS using ML and resilient ML when applied in CPS. ...
However, in building resilient systems, the possible faults that pose as security threats must be considered. ...
doi:10.1109/comst.2020.3036778
fatcat:tyrz76ofxfejha5kwhoptv2hwu
Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS – a collection of Technical Notes Part 2
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Part 1 addresses: Assurance-overview and issues, Resilience and Safety Requirements, Open Systems Perspective and Formal Verification and Static Analysis of ML Systems. ...
This report provides an introduction and overview of the Technical Topic Notes (TTNs) produced in the Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS (Tigars) project. ...
Model 0 is trained on a training data set, T0, which includes 50% of the available data set. ...
arXiv:2003.00790v1
fatcat:hi3tzydtcfeqngexomd6zqjtqm
« Previous
Showing results 1 — 15 out of 2,175 results