1 code implementation • 29 Feb 2024 • Jack Foster, Stefan Schoepf, Alexandra Brintrup
Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance.
no code implementations • Preprint 2024 • Stefan Schoepf, Jack Foster, Alexandra Brintrup
Second, we demonstrate the performance of ASSD in a supply chain delay prediction problem with labelling errors using real-world data where we randomly introduce various levels of labelling errors.
2 code implementations • 2 Feb 2024 • Jack Foster, Kyle Fogarty, Stefan Schoepf, Cengiz Öztireli, Alexandra Brintrup
The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance.
no code implementations • 26 Oct 2023 • Stephen Mak, Liming Xu, Tim Pearce, Michael Ostroumov, Alexandra Brintrup
Our contribution is that our decentralised approach is both scalable and considers the self-interested nature of companies.
no code implementations • 26 Oct 2023 • Stephen Mak, Liming Xu, Tim Pearce, Michael Ostroumov, Alexandra Brintrup
Our contribution is that we are the first to consider both the route allocation problem and gain sharing problem simultaneously - without access to the expensive characteristic function.
no code implementations • 13 Oct 2023 • Liming Xu, Stephen Mak, Yaniv Proselkov, Alexandra Brintrup
Recognising that this work represents an initial endeavour, we emphasise the need for continued exploration in this emerging domain.
no code implementations • 30 Sep 2023 • Luca Mungo, Alexandra Brintrup, Diego Garlaschelli, François Lafond
Network reconstruction is a well-developed sub-field of network science, but it has only recently been applied to production networks, where nodes are firms and edges represent customer-supplier relationships.
no code implementations • 15 Sep 2023 • Jack Foster, Alexandra Brintrup
Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information.
1 code implementation • 15 Aug 2023 • Jack Foster, Stefan Schoepf, Alexandra Brintrup
We present Selective Synaptic Dampening (SSD), a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data.
no code implementations • 22 Jul 2023 • Stefan Schoepf, Jack Foster, Alexandra Brintrup
Organisations often struggle to identify the causes of change in metrics such as product quality and delivery duration.
no code implementations • 22 Jul 2023 • Stefan Schoepf, Stephen Mak, Julian Senoner, Liming Xu, Netland Torbjörn, Alexandra Brintrup
Our model not only represents a promising first step towards large-scale logistics optimisation with reinforcement learning but also lays the foundation for this research stream.
no code implementations • 19 May 2023 • Alexandra Brintrup, George Baryannis, Ashutosh Tiwari, Svetan Ratchev, Giovanna Martinez-Arellano, Jatinder Singh
While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation.
no code implementations • 25 Feb 2022 • Bang Xiang Yong, Alexandra Brintrup
Learning the identity function renders the AEs useless for anomaly detection.
no code implementations • 25 Feb 2022 • Bang Xiang Yong, Alexandra Brintrup
Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake applications.
no code implementations • 19 Oct 2021 • Bang Xiang Yong, Alexandra Brintrup
This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the AE called Bayesian Autoencoders (BAE).
no code implementations • 3 Sep 2021 • Liming Xu, Stephen Mak, Alexandra Brintrup
For example, the ubiquity of IoT technology helps agents "sense" the state of affairs in a supply chain and opens up new possibilities for automation.
1 code implementation • 28 Jul 2021 • Bang Xiang Yong, Yasmin Fathy, Alexandra Brintrup
Autoencoders are unsupervised models which have been used for detecting anomalies in multi-sensor environments.
no code implementations • 28 Jul 2021 • Bang Xiang Yong, Alexandra Brintrup
In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty in a cyber-physical manufacturing system (CPMS) scenario.
1 code implementation • 28 Jul 2021 • Bang Xiang Yong, Tim Pearce, Alexandra Brintrup
After an autoencoder (AE) has learnt to reconstruct one dataset, it might be expected that the likelihood on an out-of-distribution (OOD) input would be low.
no code implementations • 22 Jul 2021 • Ajmal Aziz, Edward Elson Kosasih, Ryan-Rhys Griffiths, Alexandra Brintrup
It is anticipated that our method will be directly applicable to businesses wishing to sever links with nefarious entities and mitigate risk of supply failure.
no code implementations • 19 Jul 2021 • Jie Zhang, Alexandra Brintrup, Anisoara Calinescu, Edward Kosasih, Angira Sharma
This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue.
no code implementations • 9 Jun 2021 • Tim Pearce, Alexandra Brintrup, Jun Zhu
It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution.
no code implementations • 2 Nov 2020 • Angira Sharma, Edward Kosasih, Jie Zhang, Alexandra Brintrup, Anisoara Calinescu
This work explores the various DT features and current approaches, the shortcomings and reasons behind the delay in the implementation and adoption of digital twin.
1 code implementation • 12 Jul 2020 • Tim Pearce, Andrew Y. K. Foong, Alexandra Brintrup
This paper explores the benefits of adding structure to weight priors.
1 code implementation • 15 May 2019 • Tim Pearce, Russell Tsuchida, Mohamed Zaki, Alexandra Brintrup, Andy Neely
A simple, flexible approach to creating expressive priors in Gaussian process (GP) models makes new kernels from a combination of basic kernels, e. g. summing a periodic and linear kernel can capture seasonal variation with a long term trend.
2 code implementations • 12 Oct 2018 • Tim Pearce, Felix Leibfried, Alexandra Brintrup, Mohamed Zaki, Andy Neely
Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian.
1 code implementation • ICML 2018 • Tim Pearce, Mohamed Zaki, Alexandra Brintrup, Andy Neely
This paper considers the generation of prediction intervals (PIs) by neural networks for quantifying uncertainty in regression tasks.