[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 …
Improving adversarial robustness by learning shared information
X Yu, N Smedemark-Margulies, S Aeron… - Pattern Recognition, 2023 - Elsevier
We consider the problem of improving the adversarial robustness of neural networks while
retaining natural accuracy. Motivated by the multi-view information bottleneck formalism, we …
retaining natural accuracy. Motivated by the multi-view information bottleneck formalism, we …
Information theoretic representation distillation
Despite the empirical success of knowledge distillation, current state-of-the-art methods are
computationally expensive to train, which makes them difficult to adopt in practice. To …
computationally expensive to train, which makes them difficult to adopt in practice. To …
R2-trans: Fine-grained visual categorization with redundancy reduction
Fine-grained visual categorization (FGVC) aims to discriminate similar subcategories,
whose main challenge is the large intraclass diversities and subtle inter-class differences …
whose main challenge is the large intraclass diversities and subtle inter-class differences …
Multi-view information bottleneck without variational approximation
By" intelligently" fuse the complementary information across different views, multi-view
learning is able to improve the performance of classification task. In this work, we extend the …
learning is able to improve the performance of classification task. In this work, we extend the …
Gated information bottleneck for generalization in sequential environments
F Alesiani, S Yu, X Yu - Knowledge and Information Systems, 2023 - Springer
Deep neural networks suffer from poor generalization to unseen environments when the
underlying data distribution is different from that in the training set. By learning minimum …
underlying data distribution is different from that in the training set. By learning minimum …
Entropy-based Guidance of Deep Neural Networks for Accelerated Convergence and Improved Performance
Neural networks have dramatically increased our capacity to learn from large, high-
dimensional datasets across innumerable disciplines. However, their decisions are not …
dimensional datasets across innumerable disciplines. However, their decisions are not …
Optimal randomized approximations for matrix-based rényi's entropy
The Matrix-based Rényi's entropy enables us to directly measure information quantities from
given data without the costly probability density estimation of underlying distributions, thus …
given data without the costly probability density estimation of underlying distributions, thus …
Local intrinsic dimensional entropy
Most entropy measures depend on the spread of the probability distribution over the sample
space| X|, and the maximum entropy achievable scales proportionately with the sample …
space| X|, and the maximum entropy achievable scales proportionately with the sample …
Understanding neural networks with logarithm determinant entropy estimator
Understanding the informative behaviour of deep neural networks is challenged by misused
estimators and the complexity of network structure, which leads to inconsistent observations …
estimators and the complexity of network structure, which leads to inconsistent observations …