Neural Networks with Poincare Chaos

Marat U. Akhmet, Madina Tleubergenova, Akylbek Zhamanshin

2019

Full text Open access: Green Metadata (CSL-JSON)
DOI 10.1145/3373744.3373749
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

To make research of chaos more amenable to investigating the neural networks through differential equations, we apply the results initiated in [1,2], where the Poincare chaos is introduced. The presence of chaos is approved by existence of unpredictable solutions. The present research considers the existence and uniqueness of asymptotically stable unpredictable solution for a shunting inhibitory cellular neural network (SICNN). Appropriate examples with simulations that support the theoretical results are provided.