Unraveling the Black Box of Neural Networks: A Dynamic Extremum Mapper
Not on the map. Why?
Abstract (arXiv)
We point out that neural networks are not black boxes, and their generalization stems from the ability to dynamically map a dataset to the extrema of the model function. We further prove that the number of extrema in a neural network is positively correlated with the number of its parameters. We then propose a new algorithm that is significantly different from back-propagation algorithm, which mainly obtains the values of parameters by solving a system of linear equations. Some difficult situations, such as gradient vanishing and overfitting, can be simply explained and dealt with in this framework.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 16 references that are in the map. First posted on arXiv 5 Jul 2025.
Builds on
9 of 16 references.
References · 9
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2015Deep Learning and the Information Bottleneck Principlecited by 802
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
- 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
- 2021GAN Inversion: A Surveycited by 367
- 2018How Does Batch Normalization Help Optimization?cited by 357
- 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 105
- 2019Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Surveycited by 93
- 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
Built on by
Not cited yet.