3 citations · 10 across the 9 of their papers we have counts for
9 papers
The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
Daniel Cunnington, Mark Law, Jorge Lobo +1
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 t…
Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features?
Jack Furby, Daniel Cunnington, Dave Braines +1
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 inh…
Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs
Ioannis Mavromatis, Theodoros Spyridopoulos, Pietro Carnelli +12
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 introduce…
Symbolic Learning for Material Discovery
Daniel Cunnington, Flaviu Cipcigan, Rodrigo Neumann Barros Ferreira +1
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…
Towards a Deeper Understanding of Concept Bottleneck Models Through End-to-End Explanation
Jack Furby, Daniel Cunnington, Dave Braines +1
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…
Neuro-Symbolic Learning of Answer Set Programs from Raw Data
Daniel Cunnington, Mark Law, Jorge Lobo +1
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…
FF-NSL: Feed-Forward Neural-Symbolic Learner
Daniel Cunnington, Mark Law, Alessandra Russo +1
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 ad…
NSL: Hybrid Interpretable Learning From Noisy Raw Data
Daniel Cunnington, Alessandra Russo, Mark Law +2
Inductive Logic Programming (ILP) systems learn generalised, interpretable rules in a data-efficient manner utilising existing background knowledge. However, current ILP systems re…
Synthetic Ground Truth Generation for Evaluating Generative Policy Models
Daniel Cunnington, Graham White, Geeth de Mel
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 prefer…