Chaotic dynamic system is a nonlinear deterministic system that displays complex, noisy-like and unpredictable behavior. Control and synchronization of chaotic dynamical system have attracted a great deal of attention within the engineering community. This paper proposes an adaptive wavelet neural control (AWNC) system to synchronize two identical chaotic gyros with nonlinear damping globally. ...

On the basis of nonlinear dynamical modeling we investigate a chaos-based detector, which allows the extraction of signal frequencies in noisy chaotic interference.The detection scheme is tested by using both computer-generated chaotic data and real-life Lorenz-Sten£o (LS) chaotic circuit data respectively. The performance analysis demonstrates that signals hidden beneath the chaotic ambient no...

In ISNN’04, a novel symmetric cipher was proposed, by combining a chaotic signal and a clipped neural network (CNN) for encryption. The present paper analyzes the security of this chaotic cipher against chosen-plaintext attacks, and points out that this cipher can be broken by a chosen-plaintext attack. Experimental analyses are given to support the feasibility of the proposed attack.

A chaotic noise is one of the most important implements for information processing such as neural networks. It has been suggested that chaotic neural networks have high performance ability for information processing. In this paper, we report two designs of a compact chaotic noise generator for large integration circuits using CMOS technology. The chaotic noise is generated using map chaos. We d...

We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable and non-chaotic dynamics. This stands in stark contrast to more standard gated architectures, whose underlying dynamical systems exhibit c...

The synchronization problem is studied in this paper for a class of fractional-order chaotic neural networks. By using the Mittag-Leffler function, M-matrix and linear feedback control, a sufficient condition is developed ensuring the synchronization of such neural models with the Caputo fractional derivatives. The synchronization condition is easy to verify, implement and only relies on system...

This paper proposes a simple methodology to construct an iterative neural network which mimics a given chaotic time series. The methodology uses the Gamma test to identify a suitable (possibly irregular) embedding of the chaotic time series from which a one step predictive model may be constructed. A one-step predictive model is then constructed as a feedforward neural network trained using the...

Neural network modeling is often concerned with stimulus-driven responses, but most of the activity in the brain is internally generated. Here, we review network models of internally generated activity, focusing on three types of network dynamics: (a) sustained responses to transient stimuli, which provide a model of working memory; (b) oscillatory network activity; and (c) chaotic activity, wh...

In this paper, multi step ahead prediction of monthly sunspot real time series are carried out. This series is highly chaotic in nature [7]. This paper compares performance of proposed Jordan Elman Neural Network with TLRNN (Time lag recurrent neural network), and RNN (Recurrent neural network) for multi-step ahead (1, 6, 12, 18, 24) predictions. It is seen that the proposed neural network mode...

this paper presents a new control scheme for a class of nonlinear systems. in the proposed method, an adaptive neural network observer with rise feedback controller are applied to realize sensorless control scheme. this observer is tuned online and no exact information of nonlinear term of plant is required. so, this characteristic can compensate mismodeling phenomena. also, a new controller ca...