No article text was recorded for this version.
gradient shattering
Version 1 of 134 papers35 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
- Blog: Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
- Blog: Explaining 3D Point Cloud Semantic Segmentation Models Through Adversarial Attacks
- Blog: Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions
- Blog: How Sensitive are Sensitivity-Based Explanations?
- Blog: Saliency-driven Word Alignment Interpretation for Neural Machine Translation
- Blog: Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
- Blog: Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution
- Blog: A Fresh Look at Sanity Checks for Saliency Maps
- Blog: Epistemic Uncertainty Quantification for Pretrained Neural Networks
- Blog: SAM: The Sensitivity of Attribution Methods to Hyperparameters
- Blog: Path-sampled integrated gradients
- Blog: On Smoother Attributions using Neural Stochastic Differential Equations
- Blog: Model Guidance via Robust Feature Attribution
- Blog: Negative Flux Aggregation to Estimate Feature Attributions
- Blog: Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations
- Blog: ScoreCAM++: Gated Score-Weighted Visual Explanations for CNNs
- Blog: Quantum Gradient Class Activation Map for Model Interpretability
- Blog: Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
- Blog: DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
- Blog: MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope
- Blog: Towards Robust, Locally Linear Deep Networks
- Blog: Towards Visually Explaining Video Understanding Networks with Perturbation
- Blog: Relevance-CAM: Your Model Already Knows Where To Look
- Blog: Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
- Blog: DAVE: Distribution-Aware Attribution via ViT Gradient Decomposition
- Blog: Higher-Order Explanations of Graph Neural Networks via Relevant Walks
- Blog: FAM: Visual Explanations for the Feature Representations from Deep Convolutional Networks
- Blog: Towards best practice in explaining neural network decisions with LRP
- Blog: Visualizing Deep Networks by Optimizing with Integrated Gradients
- Blog: A Functional Information Perspective on Model Interpretation
- Blog: Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition
- Blog: SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective
- Blog: Simplified Concrete Dropout - Improving the Generation of Attribution Masks for Fine-grained Classification
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_shattering_9e35bd7a,
title = {gradient shattering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-shattering/rdr_9e35bd7a29f7460dbb795dd79583001b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_gradient_shattering_9e35bd7a_v1,
title = {gradient shattering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-shattering/rdr_9e35bd7a29f7460dbb795dd79583001b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}