Recent advances in trustworthy explainable artificial intelligence: Status, challenges, and perspectives

A Rawal, J McCoy, DB Rawat… - IEEE Transactions …, 2021‏ - ieeexplore.ieee.org
Artificial intelligence (AI) and machine learning (ML) have come a long way from the earlier
days of conceptual theories, to being an integral part of today's technological society. Rapid …

Neuro-symbolic artificial intelligence: a survey

BP Bhuyan, A Ramdane-Cherif, R Tomar… - Neural Computing and …, 2024‏ - Springer
The goal of the growing discipline of neuro-symbolic artificial intelligence (AI) is to develop
AI systems with more human-like reasoning capabilities by combining symbolic reasoning …

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 …

Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning

AA Garcez, M Gori, LC Lamb, L Serafini… - arxiv preprint arxiv …, 2019‏ - arxiv.org
Current advances in Artificial Intelligence and machine learning in general, and deep
learning in particular have reached unprecedented impact not only across research …

Deep logic networks: Inserting and extracting knowledge from deep belief networks

SN Tran, ASA Garcez - IEEE transactions on neural networks …, 2016‏ - ieeexplore.ieee.org
Developments in deep learning have seen the use of layerwise unsupervised learning
combined with supervised learning for fine-tuning. With this layerwise approach, a deep …

Innovative second-generation wavelets construction with recurrent neural networks for solar radiation forecasting

G Capizzi, C Napoli, F Bonanno - IEEE Transactions on neural …, 2012‏ - ieeexplore.ieee.org
Solar radiation prediction is an important challenge for the electrical engineer because it is
used to estimate the power developed by commercial photovoltaic modules. This paper …

Bilateral sensitivity analysis: a better understanding of a neural network

H Zhang, Y Jiang, J Wang, K Zhang, NR Pal - International Journal of …, 2022‏ - Springer
A model-independent sensitivity analysis for (deep) neural network, Bilateral sensitivity
analysis (BiSA), is proposed to measure the relationship or dependency between neurons …

Controlling recurrent neural networks by conceptors

H Jaeger - arxiv preprint arxiv:1403.3369, 2014‏ - arxiv.org
The human brain is a dynamical system whose extremely complex sensor-driven neural
processes give rise to conceptual, logical cognition. Understanding the interplay between …

An empirical evaluation of rule extraction from recurrent neural networks

Q Wang, K Zhang, AG Ororbia II, X **ng, X Liu… - Neural …, 2018‏ - direct.mit.edu
Rule extraction from black box models is critical in domains that require model validation
before implementation, as can be the case in credit scoring and medical diagnosis. Though …

Linear priors mined and integrated for transparency of blast furnace black-box SVM model

S Chen, C Gao - IEEE Transactions on Industrial Informatics, 2019‏ - ieeexplore.ieee.org
Black-box models are a kind of effective means to describe extremely complex systems,
such as blast furnaces. However, an evident deficiency for them lies in the lack of …