Entropy Bifurcation of Neural Networks on Cayley Trees

DOI10.1142/S0218127420500157zbMATH Open1436.37008arXiv1706.09283OpenAlexW3005842055MaRDI QIDQ5220448FDOQ5220448

Authors: Jung-Chao Ban, Chih-Hung Chang, Nai-Zhu Huang 

Publication date: 23 March 2020

Published in: International Journal of Bifurcation and Chaos in Applied Sciences and Engineering (Search for Journal in Brave)

Abstract: It has been demonstrated that excitable media with a tree structure performed better than other network topologies, it is natural to consider neural networks defined on Cayley trees. The investigation of a symbolic space called tree-shift of finite type is important when it comes to the discussion of the equilibrium solutions of neural networks on Cayley trees. Entropy is a frequently used invariant for measuring the complexity of a system, and constant entropy for an open set of coupling weights between neurons means that the specific network is stable. This paper gives a complete characterization for entropy spectrum of neural networks on Cayley trees and reveals whether the entropy bifurcates when the coupling weights change.

Full work available at URL: https://arxiv.org/abs/1706.09283

Recommendations

• THE ENTROPY OF STATIONARY SOLUTIONS' MAP OF CELLULAR NEURAL NETWORKS
• ON THE MONOTONICITY OF ENTROPY FOR MULTILAYER CELLULAR NEURAL NETWORKS
• ON THE DENSE ENTROPY OF TWO-DIMENSIONAL INHOMOGENEOUS CELLULAR NEURAL NETWORKS
• Complexity of neural networks on Fibonacci-Cayley tree
• Route to chaos in a branching model of neural network dynamics
• Horseshoe and topological entropy estimate of a class of three-dimensional cellular neural networks
• Entropy landscape of solutions in the binary perceptron problem

zbMATH Keywords

neural networksminimal entropyCayley treeentropy spectrumseparation propertylearning problem

Mathematics Subject Classification ID

Trees (05C05) Neural networks for/in biological studies, artificial life and related topics (92B20) Entropy and other invariants, isomorphism, classification in ergodic theory (37A35) Symbolic dynamics (37B10)

Cites Work

• Learning deep architectures for AI
• Deep learning
• Gibbs measures on Cayley trees
• Cellular neural networks: theory
• On Li-Yorke pairs
• An Introduction to Symbolic Dynamics and Coding
• Neural networks and physical systems with emergent collective computational abilities
• Devaney's chaos or 2-scattering implies Li-Yorke's chaos
• Spatial complexity in multi-layer cellular neural networks
• Multidimensional sofic shifts without separation and their factors
• A characterization of the entropies of multidimensional shifts of finite type
• Computing bounds for entropy of stationary \(\mathbb{Z}^d\) Markov random fields
• Approximating entropy for a class of \(\mathbb Z^2\) Markov random fields and pressure for a class of functions on \(\mathbb Z^2\) shifts of finite type
• Chaos
• Entropy gaps and locally maximal entropy in $\mathbb{Z}^d$ subshifts
• Sofic tree-shifts
• Tree-shifts of finite type
• CELLULAR NEURAL NETWORKS: LOCAL PATTERNS FOR GENERAL TEMPLATES
• A description of harmonic functions via properties of the group representation of the Cayley tree.
• Ergodic theory and dynamical systems. Translated from the French by Reinie Erné
• Realization problem of multi-layer cellular neural networks
• Mixing properties of tree-shifts
• Tree-shifts: the entropy of tree-shifts of finite type
• Tree-shifts: Irreducibility, mixing, and the chaos of tree-shifts

Cited In (4)

• ON THE MONOTONICITY OF ENTROPY FOR MULTILAYER CELLULAR NEURAL NETWORKS
• Horseshoe and topological entropy estimate of a class of three-dimensional cellular neural networks
• Complexity of neural networks on Fibonacci-Cayley tree
• Tree-structured neural networks: spatiotemporal dynamics and optimal control

Uses Software

• Fuzzy ARTMAP

This page was built for publication: Entropy Bifurcation of Neural Networks on Cayley Trees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5220448)