Estimation of the basin of attractions in CNNs

Mladenov, Valeri; Leenaerts, D.M.W.; Uhlmann, Friedrich

doi:10.1109/81.668869

Cited by 4 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For what concerns the second task, i.e. the evaluation of the domains of attraction, no result is practically available, if we except small networks References [20,21] and some estimations Reference [35].…”

Section: Cnn Design Methods and Problemsmentioning

confidence: 99%

Template design methods for binary stable cellular neural networks

Gilli

Civalleri

2002

Circuit Theory & Apps

View full text Add to dashboard Cite

SUMMARYStable cellular neural networks with binary outputs implement a non-linear mapping between sets of input and output images. Such a mapping is studied in detail. We prove two theorems: the ÿrst one yields a su cient condition in order that the non-linear mapping be well-deÿned; the second one yields a condition, that allows to describe the mapping through a simple algorithm based on the sign of the initial derivatives. Then we enunciate two additional theorems and two corollaries, that identify the class of templates satisfying the above condition: such a class is shown to be rather large and include, as particular cases, the monotonic templates, and several kinds of non-monotonic templates. Finally, a rigorous design procedure is proposed.

show abstract

Section: Cnn Design Methods and Problemsmentioning

confidence: 99%

Template design methods for binary stable cellular neural networks

Gilli

Civalleri

2002

Circuit Theory & Apps

View full text Add to dashboard Cite

show abstract

A Novel Network Behavior Model Based on Generalized Cellular Automaton

Shuai

2008

Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence

View full text Add to dashboard Cite

A New Generalized Cellular Automaton Approach to Model Behavior of Networks

Shuai

2008

2008 Fourth International Conference on Natural Computation

View full text Add to dashboard Cite

This paper presents a new approach based on the generalized cellular automaton to model the dynamic behavior of computer networks. 1 The proposed approach can fully consider the autonomy of network agents, the interactions among agents, the macroscopic performance of agent colonies with different granularity, and the influences of concurrent emergent events in the networks. The simulation on the network dynamic behaviors shows the effectiveness and validation of the proposed methodology.

show abstract

Estimation of the basin of attractions in CNNs

Cited by 4 publications

References 9 publications

Template design methods for binary stable cellular neural networks

Template design methods for binary stable cellular neural networks

A Novel Network Behavior Model Based on Generalized Cellular Automaton

A New Generalized Cellular Automaton Approach to Model Behavior of Networks

Contact Info

Product

Resources

About