Daniel Cunnington
YOU?
Author Swipe
View article: The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning Open
Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems, as interpretable symbolic techniques provide formal behaviour guarantees. The challenge is how to effectively integrate neural and symbolic computation, to…
View article: Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features?
Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features? Open
Concept Bottleneck Models (CBMs) are regarded as inherently interpretable because they first predict a set of human-defined concepts which are used to predict a task label. For inherent interpretability to be fully realised, and ensure tru…
View article: Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs
Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs Open
The way we travel is changing rapidly and Cooperative Intelligent Transportation Systems (C-ITSs) are at the forefront of this evolution. However, the adoption of C-ITSs introduces new risks and challenges, making cybersecurity a top prior…
View article: Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs
Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs Open
The way we travel is changing rapidly, and Cooperative Intelligent Transportation Systems (C-ITSs) are at the forefront of this evolution. However, the adoption of C-ITSs introduces new risks and challenges, making cybersecurity a top prio…
View article: Symbolic Learning for Material Discovery
Symbolic Learning for Material Discovery Open
Discovering new materials is essential to solve challenges in climate change, sustainability and healthcare. A typical task in materials discovery is to search for a material in a database which maximises the value of a function. That func…
View article: Neuro-Symbolic Learning of Answer Set Programs from Raw Data
Neuro-Symbolic Learning of Answer Set Programs from Raw Data Open
One of the ultimate goals of Artificial Intelligence is to assist humans in complex decision making. A promising direction for achieving this goal is Neuro-Symbolic AI, which aims to combine the interpretability of symbolic techniques with…
View article: Towards a Deeper Understanding of Concept Bottleneck Models Through End-to-End Explanation
Towards a Deeper Understanding of Concept Bottleneck Models Through End-to-End Explanation Open
Concept Bottleneck Models (CBMs) first map raw input(s) to a vector of human-defined concepts, before using this vector to predict a final classification. We might therefore expect CBMs capable of predicting concepts based on distinct regi…
View article: FFNSL: Feed-Forward Neural-Symbolic Learner
FFNSL: Feed-Forward Neural-Symbolic Learner Open
Logic-based machine learning aims to learn general, interpretable knowledge in a data-efficient manner. However, labelled data must be specified in a structured logical form. To address this limitation, we propose a neural-symbolic learnin…
View article: Neuro-Symbolic Learning of Answer Set Programs from Raw Data
Neuro-Symbolic Learning of Answer Set Programs from Raw Data Open
One of the ultimate goals of Artificial Intelligence is to assist humans in complex decision making. A promising direction for achieving this goal is Neuro-Symbolic AI, which aims to combine the interpretability of symbolic techniques with…
View article: FF-NSL: Feed-Forward Neural-Symbolic Learner
FF-NSL: Feed-Forward Neural-Symbolic Learner Open
Logic-based machine learning aims to learn general, interpretable knowledge in a data-efficient manner. However, labelled data must be specified in a structured logical form. To address this limitation, we propose a neural-symbolic learnin…
View article: NSL: Hybrid Interpretable Learning From Noisy Raw Data
NSL: Hybrid Interpretable Learning From Noisy Raw Data Open
Inductive Logic Programming (ILP) systems learn generalised, interpretable rules in a data-efficient manner utilising existing background knowledge. However, current ILP systems require training examples to be specified in a structured log…
View article: Synthetic Ground Truth Generation for Evaluating Generative Policy Models
Synthetic Ground Truth Generation for Evaluating Generative Policy Models Open
Generative Policy-based Models aim to enable a coalition of systems, be they devices or services to adapt according to contextual changes such as environmental factors, user preferences and different tasks whilst adhering to various constr…
View article: Synthetic Ground Truth Generation for Evaluating Generative Policy\n Models
Synthetic Ground Truth Generation for Evaluating Generative Policy\n Models Open
Generative Policy-based Models aim to enable a coalition of systems, be they\ndevices or services to adapt according to contextual changes such as\nenvironmental factors, user preferences and different tasks whilst adhering to\nvarious con…