Application of Sensitivity Analysis Methods for Studying Neural Network Models
math.NA, cs.LG, cs.NA
Submitted: 2025-04-21
Updated: 2025-04-21
Code: https://github.com/LUCI1a/diabetes_prediction
Terminology
Sources
- Neural Video Compression using Spatio-Temporal Priors
- Hopfield Networks is All You Need
- Fast Feature Fool: A data independent approach to universal adversarial perturbations
- Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- Operator learning meets inverse problems: A probabilistic perspective
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers