[HTML][HTML] An empirical survey on explainable ai technologies: Recent trends, use-cases, and categories from technical and application perspectives
M Nagahisarchoghaei, N Nur, L Cummins, N Nur… - Electronics, 2023 - mdpi.com
In a wide range of industries and academic fields, artificial intelligence is becoming
increasingly prevalent. AI models are taking on more crucial decision-making tasks as they …
increasingly prevalent. AI models are taking on more crucial decision-making tasks as they …
Negation of the quantum mass function for multisource quantum information fusion with its application to pattern classification
F Xiao, W Pedrycz - IEEE Transactions on Pattern Analysis and …, 2022 - ieeexplore.ieee.org
In artificial intelligence systems, a question on how to express the uncertainty in knowledge
remains an open issue. The negation scheme provides a new perspective to solve this …
remains an open issue. The negation scheme provides a new perspective to solve this …
[PDF][PDF] Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities.
We present a review on the recent advances and emerging opportunities around the theme
of analyzing deep neural networks (DNNs) with information-theoretic methods. We first …
of analyzing deep neural networks (DNNs) with information-theoretic methods. We first …
Understanding autoencoders with information theoretic concepts
S Yu, JC Principe - Neural Networks, 2019 - Elsevier
Despite their great success in practical applications, there is still a lack of theoretical and
systematic methods to analyze deep neural networks. In this paper, we illustrate an …
systematic methods to analyze deep neural networks. In this paper, we illustrate an …
Causal recurrent variational autoencoder for medical time series generation
H Li, S Yu, J Principe - Proceedings of the AAAI conference on artificial …, 2023 - ojs.aaai.org
We propose causal recurrent variational autoencoder (CR-VAE), a novel generative model
that is able to learn a Granger causal graph from a multivariate time series x and …
that is able to learn a Granger causal graph from a multivariate time series x and …
Relevant information undersampling to support imbalanced data classification
Traditional classification algorithms suppose that the sample distribution among classes is
balanced. Yet, such an assumption leads to biased performance over the majority class …
balanced. Yet, such an assumption leads to biased performance over the majority class …
Deep adaptively-enhanced hashing with discriminative similarity guidance for unsupervised cross-modal retrieval
Cross-modal hashing that leverages hash functions to project high-dimensional data from
different modalities into the compact common hamming space, has shown immeasurable …
different modalities into the compact common hamming space, has shown immeasurable …
Hrel: Filter pruning based on high relevance between activation maps and class labels
This paper proposes an Information Bottleneck theory based filter pruning method that uses
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
a statistical measure called Mutual Information (MI). The MI between filters and class labels …
Ci-gnn: A granger causality-inspired graph neural network for interpretable brain network-based psychiatric diagnosis
There is a recent trend to leverage the power of graph neural networks (GNNs) for brain-
network based psychiatric diagnosis, which, in turn, also motivates an urgent need for …
network based psychiatric diagnosis, which, in turn, also motivates an urgent need for …
Understanding convolutional neural networks with information theory: An initial exploration
A novel functional estimator for Rényi's α-entropy and its multivariate extension was recently
proposed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected …
proposed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected …