Emerging trends in deep learning for credit scoring: A review

Y Hayashi - Electronics, 2022 - mdpi.com
This systematic review aims to provide deep insights on emerging trends in, and the
potential of, advanced deep learning techniques, such as machine learning algorithms …

[HTML][HTML] Advanced insights through systematic analysis: Mapping future research directions and opportunities for xAI in deep learning and artificial intelligence used in …

M Pawlicki, A Pawlicka, R Kozik, M Choraś - Neurocomputing, 2024 - Elsevier
This paper engages in a comprehensive investigation concerning the application of
Explainable Artificial Intelligence (xAI) within the context of deep learning and Artificial …

Explainable artificial intelligence 101: Techniques, applications and challenges

W Kurek, M Pawlicki, A Pawlicka, R Kozik… - … Conference on Intelligent …, 2023 - Springer
Artificial Intelligence (AI) systems have grown commonplace in modern life, with various
applications from customized suggestions to self-driving vehicles. As these systems get …

Rule learning by modularity

A Nössig, T Hell, G Moser - Machine Learning, 2024 - Springer
In this paper, we present a modular methodology that combines state-of-the-art methods in
(stochastic) machine learning with well-established methods in inductive logic programming …

Extraction of the association rules from artificial neural networks based on the multiobjective optimization

D Yedjour, H Yedjour, S Chouraqui - Network: Computation in …, 2022 - Taylor & Francis
ABSTRACT Artificial Neural Network (ANN) is one of the powerful techniques of machine
learning. It has shown its effectiveness in both prediction and classification problems …

Poem: Pattern-oriented explanations of CNN models

V Dadvar - 2022 - uwspace.uwaterloo.ca
While Convolutional Neural Networks (CNN) achieve state-of-the-art predictive performance
in applications such as computer vision, their predictions are difficult to explain, similar to …

[PDF][PDF] D3. 1 Specificability, explainability, traceability, and robustness proof-of-concept and argumentation

TH Bui, M Ulan, R Lowe - dissemination level PU, 2024 - safexplain.eu
This document reports the interim results (as of M18) of SAFEXPLAIN's FUSA-aware DL
solution within the scope of WP3-Deep Learning. The work has been performed in …

Rule Extraction in Trained Feedforward Deep Neural Networks: Integrating Cosine Similarity and Logic for Explainability

PA Negro, C Pons - International Journal of Artificial Intelligence and …, 2024 - igi-global.com
Explainability is a key aspect of machine learning, necessary for ensuring transparency and
trust in decision-making processes. As machine learning models become more complex, the …

Извлечение правил нейросетевого регулятора при построении когнитивных систем автоматического управления

ДВ Маршаков, ОЛ Цветкова - Вестник ВГУ. Серия: Системный …, 2024 - journals.vsu.ru
Когнитивные технологии входят в один из самых «интеллектуальных» разделов
теории искусственного интеллекта. Особое место в интеллектуальных системах …

Truth Table Deep Convolutional Neural Network, A New SAT-Encodable Architecture-Application To Complete Robustness

A Benamira, T Peyrin, B Hooi - openreview.net
With the expanding role of neural networks, the need for formal verification of their behavior,
interpretability and human post-processing has become critical in many applications. In …