Logic tensor networks

S Badreddine, AA Garcez, L Serafini, M Spranger - Artificial Intelligence, 2022‏ - Elsevier
Attempts at combining logic and neural networks into neurosymbolic approaches have been
on the increase in recent years. In a neurosymbolic system, symbolic knowledge assists …

Logic-induced diagnostic reasoning for semi-supervised semantic segmentation

C Liang, W Wang, J Miao… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
Recent advances in semi-supervised semantic segmentation have been heavily reliant on
pseudo labeling to compensate for limited labeled data, disregarding the valuable relational …

[HTML][HTML] Analyzing differentiable fuzzy logic operators

E Van Krieken, E Acar, F Van Harmelen - Artificial Intelligence, 2022‏ - Elsevier
The AI community is increasingly putting its attention towards combining symbolic and
neural approaches, as it is often argued that the strengths and weaknesses of these …

EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage …

N Díaz-Rodríguez, A Lamas, J Sanchez, G Franchi… - Information …, 2022‏ - Elsevier
Abstract The latest Deep Learning (DL) models for detection and classification have
achieved an unprecedented performance over classical machine learning algorithms …

Neural-symbolic integration: A compositional perspective

E Tsamoura, T Hospedales, L Michael - Proceedings of the AAAI …, 2021‏ - ojs.aaai.org
Despite significant progress in the development of neural-symbolic frameworks, the question
of how to integrate a neural and a symbolic system in a compositional manner remains …

Transfer learning with synthetic corpora for spatial role labeling and reasoning

R Mirzaee, P Kordjamshidi - arxiv preprint arxiv:2210.16952, 2022‏ - arxiv.org
Recent research shows synthetic data as a source of supervision helps pretrained language
models (PLM) transfer learning to new target tasks/domains. However, this idea is less …

Analyzing differentiable fuzzy implications

E Van Krieken, E Acar, F Van Harmelen - arxiv preprint arxiv:2006.03472, 2020‏ - arxiv.org
Combining symbolic and neural approaches has gained considerable attention in the AI
community, as it is often argued that the strengths and weaknesses of these approaches are …

Injecting domain knowledge in neural networks: a controlled experiment on a constrained problem

M Silvestri, M Lombardi, M Milano - … , CPAIOR 2021, Vienna, Austria, July 5 …, 2021‏ - Springer
Recent research has shown how Deep Neural Networks trained on historical solution pools
can tackle CSPs to some degree, with potential applications in problems with implicit soft …

Teaching the old dog new tricks: Supervised learning with constraints

F Detassis, M Lombardi, M Milano - … of the AAAI Conference on Artificial …, 2021‏ - ojs.aaai.org
Adding constraint support in Machine Learning has the potential to address outstanding
issues in data-driven AI systems, such as safety and fairness. Existing approaches typically …

Knowledge enhanced neural networks for relational domains

A Daniele, L Serafini - International Conference of the Italian Association …, 2022‏ - Springer
In the recent past, there has been a growing interest in Neural-Symbolic Integration
frameworks, ie, hybrid systems that integrate connectionist and symbolic approaches to …