Search Results for author:
Found 27 papers, 9 papers with code
Loss-Free Machine Unlearning
Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance.
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
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.
Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization
The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance.
Coalitional Bargaining via Reinforcement Learning: An Application to Collaborative Vehicle Routing
Our contribution is that our decentralised approach is both scalable and considers the self-interested nature of companies.
Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach
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.
Towards Autonomous Supply Chains: Definition, Characteristics, Conceptual Framework, and Autonomy Levels
Recognising that this work represents an initial endeavour, we emphasise the need for continued exploration in this emerging domain.
Reconstructing supply networks
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.
Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization
Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information.
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
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.
Identifying contributors to supply chain outcomes in a multi-echelon setting: a decentralised approach
Organisations often struggle to identify the causes of change in metrics such as product quality and delivery duration.
Unlocking Carbon Reduction Potential with Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem
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.
Trustworthy, responsible, ethical AI in manufacturing and supply chains: synthesis and emerging research questions
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.
Do autoencoders need a bottleneck for anomaly detection?
Learning the identity function renders the AEs useless for anomaly detection.
Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection
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.
Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning
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).
Will bots take over the supply chain? Revisiting Agent-based supply chain automation
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.
Bayesian Autoencoders for Drift Detection in Industrial Environments
Autoencoders are unsupervised models which have been used for detecting anomalies in multi-sensor environments.
Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System
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.
Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection
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.
Data Considerations in Graph Representation Learning for Supply Chain Networks
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.
Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems
This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue.
Understanding Softmax Confidence and Uncertainty
It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution.
Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions
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.
Structured Weight Priors for Convolutional Neural Networks
This paper explores the benefits of adding structure to weight priors.
Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions
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.
Uncertainty in Neural Networks: Approximately Bayesian Ensembling
Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian.
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
This paper considers the generation of prediction intervals (PIs) by neural networks for quantifying uncertainty in regression tasks.
