On the structure of multilayer cellular neural networks: complexity between two layers
From MaRDI portal
Hausdorff and packing measures (28A78) Symbolic dynamics (37B10) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Neural nets and related approaches to inference from stochastic processes (62M45) Neural networks for/in biological studies, artificial life and related topics (92B20) Applications of graph theory to circuits and networks (94C15)
Abstract: Let be the solution space of an -layer cellular neural network, and let and be the hidden spaces, where . ( is called the output space.) The classification and the existence of factor maps between two hidden spaces, that reaches the same topological entropies, are investigated in [Ban et al., J.~Differential Equations extbf{252}, 4563-4597, 2012]. This paper elucidates the existence of factor maps between those hidden spaces carrying distinct topological entropies. For either case, the Hausdorff dimension and can be calculated. Furthermore, the dimension of and are related upon the factor map between them.
Recommendations
Cited in
(8)- Realization problem of multi-layer cellular neural networks
- Spatial complexity in multi-layer cellular neural networks
- When are two multi-layer cellular neural networks the same?
- Solution structure of multi-layer neural networks with initial condition
- scientific article; zbMATH DE number 2018620 (Why is no real title available?)
- On the structure of two-layer cellular neural networks
- On the structure of multi-layer cellular neural networks
- Diamond in multi-layer cellular neural networks
This page was built for publication: On the structure of multilayer cellular neural networks: complexity between two layers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2974180)