A-nesi: A scalable approximate method for probabilistic neurosymbolic inference

E van Krieken, T Thanapalasingam… - Advances in …, 2023‏ - proceedings.neurips.cc
We study the problem of combining neural networks with symbolic reasoning. Recently
introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as …

Semantic strengthening of neuro-symbolic learning

K Ahmed, KW Chang… - … Conference on Artificial …, 2023‏ - proceedings.mlr.press
Numerous neuro-symbolic approaches have recently been proposed typically with the goal
of adding symbolic knowledge to the output layer of a neural network. Ideally, such losses …

Knowledge enhanced neural networks for point cloud semantic segmentation

E Grilli, A Daniele, M Bassier, F Remondino, L Serafini - Remote Sensing, 2023‏ - mdpi.com
Deep learning approaches have sparked much interest in the AI community during the last
decade, becoming state-of-the-art in domains such as pattern recognition, computer vision …

Exploiting t-norms for deep learning in autonomous driving

MCÄ Stoian, E Giunchiglia, T Lukasiewicz - arxiv preprint arxiv …, 2024‏ - arxiv.org
Deep learning has been at the core of the autonomous driving field development, due to the
neural networks' success in finding patterns in raw data and turning them into accurate …

A novel Elman neural network based on Gaussian kernel and improved SOA and its applications

Z Liu, D Ning, J Hou - Expert Systems with Applications, 2024‏ - Elsevier
To address challenges encountered in traditional Elman neural networks (ENNs), such as
low convergence accuracy, difficulties in hyperparameter selection, and issues with gradient …

Uller: A unified language for learning and reasoning

E van Krieken, S Badreddine, R Manhaeve… - … Conference on Neural …, 2024‏ - Springer
The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and
reasoning, has recently experienced significant growth. There now are a wide variety of …

Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation Through Collaborative Error Revision

J Kim, T Kim, J Choo - European Conference on Computer Vision, 2024‏ - Springer
Recent advances in interactive keypoint estimation methods have enhanced accuracy while
minimizing user intervention. However, these methods require user input for error correction …

Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints

MCÄ Stoian, E Giunchiglia - arxiv preprint arxiv:2502.18237, 2025‏ - arxiv.org
Synthetic tabular data generation has traditionally been a challenging problem due to the
high complexity of the underlying distributions that characterise this type of data. Despite …

[HTML][HTML] Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation

P Chatterjee, S Siddiqui, RSA Kareem, S Rao - Cancers, 2025‏ - mdpi.com
Cervical cancer screening through computer-aided diagnosis often faces challenges like
inaccurate segmentation and incomplete boundary detection in colposcopic images. This …

Simple and Effective Transfer Learning for Neuro-Symbolic Integration

A Daniele, T Campari, S Malhotra, L Serafini - International Conference on …, 2024‏ - Springer
Deep Learning (DL) techniques have achieved remarkable successes in recent years.
However, their ability to generalize and execute reasoning tasks remains a challenge. A …