# A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks

arXiv: https://arxiv.org/abs/2407.09585 · HTML: https://mlsanity.com/paper/2407.09585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Explainable Artificial Intelligence Approaches: A Survey](https://mlsanity.com/paper/2101.09429/) (2021)
- [Renormalization in the neural network-quantum field theory correspondence](https://mlsanity.com/paper/2212.11811/) (2022)
- [Scope and Sense of Explainability for AI-Systems](https://mlsanity.com/paper/2112.10551/) (2021)
- [On The Potential of The Fractal Geometry and The CNNs Ability to Encode it](https://mlsanity.com/paper/2401.04141/) (2024)

## Abstract (arXiv)

This paper introduces a scale-invariant methodology employing textitFractal Geometry to analyze and explain the nonlinear dynamics of complex connectionist systems. By leveraging architectural self-similarity in Deep Neural Networks (DNNs), we quantify fractal dimensions and textitroughness to deeply understand their dynamics and enhance the quality of textitintrinsic explanations. Our approach integrates principles from Chaos Theory to improve visualizations of fractal evolution and utilizes a Graph-Based Neural Network for reconstructing network topology. This strategy aims at advancing the textitintrinsic explainability of connectionist Artificial Intelligence (AI) systems.