A Scale-Invariant Diagnostic Approach Towards Understanding Dynamics of Deep Neural Networks
This work addresses the challenge of explainability in AI systems for researchers and practitioners, though it appears incremental as it builds on existing concepts like fractal geometry and chaos theory.
The paper tackled the problem of understanding the nonlinear dynamics of deep neural networks by introducing a scale-invariant methodology using fractal geometry, resulting in enhanced intrinsic explainability through quantification of fractal dimensions and roughness.
This paper introduces a scale-invariant methodology employing \textit{Fractal 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 \textit{roughness} to deeply understand their dynamics and enhance the quality of \textit{intrinsic} 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 \textit{intrinsic} explainability of connectionist Artificial Intelligence (AI) systems.