Learning Topological Horseshoe via Deep Neural Networks

被引：1

作者：

Yang, Xiao-Song ^{[1
,2
]}

Cheng, Junfeng ^{[1
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Math & Stat, Wuhan 430074, Peoples R China

[2] Huazhong Univ Sci & Technol, Hubei Key Lab Engn Modeling & Sci Comp, Wuhan 430074, Peoples R China

来源：

INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS | 2024年 / 34卷 / 04期

关键词：

Poincare map; topological horseshoe; chaos; deep neural network;

D O I：

10.1142/S021812742430009X

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Deep Neural Networks (DNNs) have been successfully applied to investigations of numerical dynamics of finite-dimensional nonlinear systems such as ODEs instead of finding numerical solutions to ODEs via the traditional Runge-Kutta method and its variants. To show the advantages of DNNs, in this paper, we demonstrate that the DNNs are more efficient in finding topological horseshoes in chaotic dynamical systems.

引用

页数：11

共 50 条

[1] Deep learning for steganalysis via convolutional neural networks
Qian, Yinlong
Dong, Jing
Wang, Wei
Tan, Tieniu
MEDIA WATERMARKING, SECURITY, AND FORENSICS 2015, 2015, 9409
[2] Characterizing Learning Dynamics of Deep Neural Networks via Complex Networks
La Malfa, Emanuele
La Malfa, Gabriele
Nicosia, Giuseppe
Latora, Vito
2021 IEEE 33RD INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2021), 2021, : 344 - 351
[3] Learning Deep Architectures via Generalized Whitened Neural Networks
Luo, Ping
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
[4] Enhancing deep neural networks via multiple kernel learning
Lauriola, Ivano
Gallicchio, Claudio
Aiolli, Fabio
PATTERN RECOGNITION, 2020, 101
[5] Learning Deep Graph Representations via Convolutional Neural Networks
Ye, Wei
Askarisichani, Omid
Jones, Alex
Singh, Ambuj
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (05) : 2268 - 2279
[6] Deep neural networks watermark via universal deep hiding and metric learning
Zhicheng Ye
Xinpeng Zhang
Guorui Feng
Neural Computing and Applications, 2024, 36 : 7421 - 7438
[7] Deep neural networks watermark via universal deep hiding and metric learning
Ye, Zhicheng
Zhang, Xinpeng
Feng, Guorui
NEURAL COMPUTING & APPLICATIONS, 2024, 36 (13): : 7421 - 7438
[8] Computing Topological Invariants of Deep Neural Networks
Zhang, Xiujun
Idrees, Nazeran
Kanwal, Salma
Saif, Muhammad Jawwad
Saeed, Fatima
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
[9] TOPOLOGICAL ADVERSARIAL ATTACKS ON GRAPH NEURAL NETWORKS VIA PROJECTED META LEARNING
Aburidi, Mohammed
Marcia, Roummel
IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS 2024, IEEE EAIS 2024, 2024, : 330 - 337
[10] Model selection in Bayesian neural networks via horseshoe priors
Ghosh, Soumya
Yao, Jiayu
Doshi-Velez, Finale
Journal of Machine Learning Research, 2019, 20

← 1 2 3 4 5 →