Original Hebbian encoding scheme of bidirectional associative memory (BAM) provides a poor pattern capacity and recall performance. Based on Rosenblatt's perceptron learning algorithm, the pattern capacity of BAM is enlarged, and perfect recall of all training pattern pairs is guaranteed. However, these methods put their emphases on pattern capacity, rather than error correction capability which is another critical point of BAM. This paper analyzes the sensitivity to noise in BAM and obtains an interesting idea to improve noise immunity of BAM. Some researchers have found that the noise sensitivity of BAM relates to the minimum absolute value of net inputs (MAV). However, in this paper, the analysis on failure association shows that it is related not only to MAV but also to the variance of weights associated with synapse connections. In fact, it is a positive monotone increasing function of the quotient of MAV divided by the variance of weights. This idea provides an useful principle of improving error correction capability of BAM. Some revised encoding schemes, such as small variance learning for BAM (SVBAM), evolutionary pseudorelaxation learning for BAM (EPRLAB) and evolutionary bidirectional learning (EBL), have been introduced to illustrate the performance of this principle. All these methods perform better than their original versions in noise immunity. Moreover, these methods have no negative effect on the pattern capacity of BAM. The convergence of these methods is also discussed in this paper. If there exist solutions, EPRLAB and EBL always converge to a global optimal solution in the senses of both pattern capacity and noise immunity. However, the convergence of SVBAM may be affected by a preset function.

This paper reports a new four-dimensional continuous autonomous chaotic system, in which each equation in the system contains a 3-term cross product. Basic properties of the system are analyzed by means of Lyapunov exponents and bifurcation diagrams.

A nonlinear proportional-integral-derivative (PID) controller is constructed based on recurrent neural networks. In the control process of nonlinear multivariable systems, several nonlinear PID controllers have been adopted in parallel. Under the decoupling cost function, a decoupling control strategy is proposed. Then the stability condition of the controller is presented based on the Lyapunov theory. Simulation examples are given to show effectiveness of the proposed decoupling control.

In practice, there are many chaotic systems whose models are usually unknown or partially unknown. However, the majority of control schemes focus on model-dependent techniques. The model-free controlling problem for affine chaotic systems is investigated in this Letter. An adaptive higher-order differential feedback controller (HODFC), which does not depend on the model of the controlled chaotic system, is presented. The controller utilizes the information of the measured output and the given objective as well as extracted differentials of those via higher-order differentiator (HOD). Stability, convergence and robustness of the closed-loop system are investigated. The presented adaptive HODFC can successfully control the uncertain Lorenz system, the Chen system, the Duffing-Holmes system, the R

Abstract-Anew nonlinear neuron-activation function is introduced into the framework of an Elman network, thereby enabling the neural networkto generate chaos. Basic analysis of its fixed point stability and parameter selection criterion for chaos generation is given, and is verified via simulation studies.