Pages that link to "Item:Q5854125"
From MaRDI portal
The following pages link to On the information bottleneck theory of deep learning (Q5854125):
Displaying 16 items.
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness (Q2057701) (← links)
- Learning when to stop: a mutual information approach to prevent overfitting in profiled side-channel analysis (Q2145285) (← links)
- Understanding autoencoders with information theoretic concepts (Q2185600) (← links)
- Landscape and training regimes in deep learning (Q2231925) (← links)
- On the stability and generalization of neural networks with VC dimension and fuzzy feature encoders (Q2235467) (← links)
- Towards interpreting deep neural networks via layer behavior understanding (Q2673336) (← links)
- (Q3093241) (← links)
- Geometric compression of invariant manifolds in neural networks (Q3382321) (← links)
- Strong optimality of the normalized ML models as universal codes and information in data (Q4544616) (← links)
- Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks (Q5033517) (← links)
- Relative stability toward diffeomorphisms indicates performance in deep nets* (Q5055429) (← links)
- ChaosNet: A chaos based artificial neural network architecture for classification (Q5205680) (← links)
- Entropy and mutual information in models of deep neural networks* (Q5854116) (← links)
- Understanding Deep Learning with Statistical Relevance (Q5883923) (← links)
- Information-theoretic self-compression of multi-layered neural networks (Q6049074) (← links)
- The role of mutual information in variational classifiers (Q6134364) (← links)
