Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
F Mumuni, A Mumuni - Cognitive Systems Research, 2024 - Elsevier
We review current and emerging knowledge-informed and brain-inspired cognitive systems
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …
ESRA: a Neuro-Symbolic Relation Transformer for Autonomous Driving
Scene Graph Generation (SGG) is a powerful tool for autonomous vehicles to understand
their environment. In this paper, a novel one-stage neuro-symbolic architecture called nEuro …
their environment. In this paper, a novel one-stage neuro-symbolic architecture called nEuro …
Concept logic trees: enabling user interaction for transparent image classification and human-in-the-loop learning
Interpretable deep learning models are increasingly important in domains where transparent
decision-making is required. In this field, the interaction of the user with the model can …
decision-making is required. In this field, the interaction of the user with the model can …
Neuro-Symbolic AI in 2024: A Systematic Review
Background: The field of Artificial Intelligence has undergone cyclical periods of growth and
decline, known as AI summers and winters. Currently, we are in the third AI summer …
decline, known as AI summers and winters. Currently, we are in the third AI summer …
Enhancing Neuro-Symbolic Integration with Focal Loss: A Study on Logic Tensor Networks
Neuro-symbolic techniques such as logic tensor networks (LTNs) enable the integration of
symbolic knowledge to improve the learning capabilities of deep neural networks. LTNs in …
symbolic knowledge to improve the learning capabilities of deep neural networks. LTNs in …
Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching
Neuro-symbolic integration aims at harnessing the power of symbolic knowledge
representation combined with the learning capabilities of deep neural networks. In …
representation combined with the learning capabilities of deep neural networks. In …
L-TReiD: Logic Tensor Transformer for Re-identification
This article proposes a Neuro-Symbolic (NeSy) machine learning approach to Object Re-
identification. NeSy is an emerging branch of artificial intelligence which combines symbolic …
identification. NeSy is an emerging branch of artificial intelligence which combines symbolic …
Concept logic trees: enabling user interaction for transparent image classification and human-in-the-loop learning
D Morales Rodríguez, M Pegalajar Cuéllar… - 2024 - digibug.ugr.es
Interpretable deep learning models are increasingly important in domains where transparent
decision-making is required. In this field, the interaction of the user with themodel can …
decision-making is required. In this field, the interaction of the user with themodel can …
Scene Graph Generation in Autonomous Driving: a Neuro-symbolic approach
PEI Dimasi - 2023 - webthesis.biblio.polito.it
The 2022 study on traffic fatalities in Italy by the Italian National Institute of Statistics (ISTAT)
reports 454 daily fatalities and 561 injuries, primarily due to distractions. Then, the success …
reports 454 daily fatalities and 561 injuries, primarily due to distractions. Then, the success …
[PDF][PDF] Robust machine learning models for high dimensional data interpretation
F Manigrasso - 2024 - tesidottorato.depositolegale.it
Deep neural networks (DNNs) are highly effective in modeling complex data, like image
pixels, by employing both linear and non-linear feature representations. Their success is …
pixels, by employing both linear and non-linear feature representations. Their success is …