Distributional Properties of ReLU-Activations in Artificial Neural Networks that Learn by Memorization
- 1 May 2026
- book chapter
- Published by Springer Nature
- p. 410-423
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- Shapley value-based class activation mapping for improved explainability in neural networksThe Visual Computer, 2025
- Understanding activation patterns in artificial neural networks by exploring stochastic processes: Discriminating generalization from memorizationNeurocomputing, 2024
- RAD-BNN: Regulating activation distribution for accurate binary neural networkImage and Vision Computing, 2024
- Generalization in Deep Learning2022
- Understanding deep learning (still) requires rethinking generalizationCommunications of the ACM, 2021
- Does learning require memorization? a short tale about a long tail2020
- Empirical Study of Easy and Hard Examples in CNN Training2019
- A Data-Driven Deep Neural Network Pruning Approach Towards Efficient Digital Signal Modulation Recognition2019
- Regularizing Activation Distribution for Training Binarized Deep Networks2019
- Improving Interpretability and Regularization in Deep LearningIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017