paper-with-me

Papers

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

2024-07-12 · Ambarish Moharil, Damian Tamburri, Indika Kumara, Willem-Jan van den Heuvel, Alireza Azarfar

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.

📄 PDF Abstract BibTeX arXiv:2407.09585

Code (0)

등록된 구현이 없습니다.

Tasks

Diagnostic

Similar Papers 제목 키워드 기반

Diagnostic Benchmarks for Invariant Learning Dynamics: Empirical Validation of the Eidos Architecture

2026-02-10 · Datorien L. Anderson arxiv

We present the PolyShapes-Ideal (PSI) dataset, a suite of diagnostic benchmarks designed to isolate topological invariance -- the ability to maintain structural identity across affine transformations -- from the textural…

Multifractal features of multimodal cardiac signals: Nonlinear dynamics of exercise recovery

2025-09-27 · A. Maluckov, D. Stojanovic, M. Miletic, Lj. Hadzievski 외 arxiv

We investigate the recovery dynamics of healthy cardiac activity after physical exertion using multimodal biosignals recorded with a polycardiograph. Multifractal features derived from the singularity spectrum capture th…

Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?

2025-11-10 · Ildus Sadrtdinov, Ekaterina Lobacheva, Ivan Klimov, Mikhail Burtsev 외 arxiv

Understanding the training dynamics of deep neural networks remains a major open problem, with physics-inspired approaches offering promising insights. Building on this perspective, we develop a thermodynamic framework t…

Data driven modeling for self-similar dynamics

2023-10-12 · Ruyi Tao, Ningning Tao, Yi-Zhuang You, Jiang Zhang

Multiscale modeling of complex systems is crucial for understanding their intricacies. Data-driven multiscale modeling has emerged as a promising approach to tackle challenges associated with complex systems. On the othe…

Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay

2026-07-23 · Xiaolong Li, Zhangchen Zhou, Zhi-Qin John Xu arxiv

Most explanations of training instability focus on \emph{learning-rate criticality}, typically characterized by the Edge of Stability, beyond which optimization becomes unstable. We argue that, in practical deep neural n…