Papers by Xiangxiang Wang
New synchronization criteria for memristor-based recurrent neural networks with mixed delays
2017 International Workshop on Complex Systems and Networks (IWCSN), 2017
This paper presents global exponential synchronization of drive-response memristor-based recurren... more This paper presents global exponential synchronization of drive-response memristor-based recurrent neural networks(MRNNs) with mixed delays. Considering the bounded distributed delays and time-varying delays as a novel kind of mixed delays, the drive-response MRNNs with mixed delays are proposed. Then, a state feedback controller is designed. By using a novel lyapunov functional and inequality techniques, novel global exponential synchronization criteria on MRNNs with mixed delays are derived. Finally, a numerical example with simulation results is given to illustrate our theoretical results.
IEEE Access, 2020
Activation functions facilitate deep neural networks by introducing non-linearity to the learning... more Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The non-linearity feature gives the neural network the ability to learn complex patterns. Recently, the most widely used activation function is the Rectified Linear Unit (ReLU). Though, other various existing activation including hand-designed alternatives to ReLU have been proposed. However, none has succeeded in replacing ReLU due to their existing inconsistencies. In this work, activation function called ReLU-Memristor-like Activation Function (RMAF) is proposed to leverage benefits of negative values in neural networks. RMAF introduces a constant parameter (α) and a threshold parameter (p) making the function smooth, non-monotonous, and introduces non-linearity in the network. Our experiments show that, the RMAF works better than ReLU and other activation functions on deeper models and across number of challenging datasets. Firstly, experiments are performed by training and classifying on multi-layer perceptron (MLP) over benchmark data such as the Wisconsin breast cancer, MNIST, Iris and Car evaluation. RMAF achieves high performance of 98.74%, 99.67%, 98.81% and 99.42% respectively, compared to Sigmoid, Tanh and ReLU. Secondly, experiments were performed on convolution neural network (ResNet) over MNIST, CIFAR-10 and CIFAR-100 data and observed the proposed activation function achieves higher performance accuracy of 99.73%, 98.77% and 79.82% respectively than Tanh, ReLU and Swish. Additionally, we experimented our work on deep networks i.e. squeeze network (SqueezeNet), Dense connected neural network (DenseNet121) and ImageNet dataset, which RMAF produced the best performance. We note that, the RMAF converges faster than the other functions and can replace ReLU in any neural network due to the efficiency, scalability and its similarity to both ReLU and Swish.
Dynamic Pinning Synchronization of Fuzzy-dependent-switched Coupled Memristive Neural Networks with Mismatched Dimensions on Time Scales
IEEE Transactions on Fuzzy Systems
This paper addresses the problem of dynamic pinning synchronization of fuzzy-dependent-switched (... more This paper addresses the problem of dynamic pinning synchronization of fuzzy-dependent-switched (Fds) coupled memristive neural networks (CMNNs) with mismatched dimensions on time scales. To begin with, the probabilistic coupling delays, time scales, mismatched dimensions, and Fps rules are considered to design the novel CMNNs to improve the reliability and generalization ability of the model. Then Fds rules and dynamic pinning control (DPC) method are adopted to design the CMNNs, which can effectively promote the information exchange between the switching signals and the fuzzy processes and can improve the utilization of the communication bandwidth between the nodes of CMNNs. Meanwhile, the method of constructing auxiliary state variables is adopted here to deal with the presented model, so that the coupled and isolated systems with different dimensions can realize information exchange and data sharing. This method also provides a solution for researchers by using low-dimensional systems to estimate or synchronize high-dimensional systems. Moreover, by means of Lyapunov-Krasovskii functional, auxiliary orthogonal matrix, and some inequality processing techniques, the conditions of modified function projective synchronization (MFPS) for FdsCMNNs are derived via the DPC on time scales. Finally, two numerical examples are provided to illustrate the effectiveness of the main results.
H∞ State Estimation of Memristor-based Recurrent Neural Networks with Mixed Delay
2019 3rd International Conference on Robotics and Automation Sciences (ICRAS), 2019
This paper is concerned with studying H∞ state estimation of memristor-based recurrent neural net... more This paper is concerned with studying H∞ state estimation of memristor-based recurrent neural networks(MRNNs) with mixed delays. The MRNNs addressed is comprehensive to cover distributed-delays and time-varying delays in order to reflect the reality more closely and accurate. The delay-dependent design criteria is presented under which the resulting estimation error system is globally asymptotically stable and a prescribed performance is guaranteed in the H∞ sense by the Jensen inequality, Wirtinger inequality and reciprocally convex approach. Finally, the simulation results confirm the effectiveness of Theorem 3.1 for the design of guaranteed performance H∞ state estimator for MRNNs with mixed delays.
Novel Heterogeneous Mode-dependent Impulsive Synchronization for Piecewise T-S Fuzzy Probabilistic Coupled Delayed Neural Networks
IEEE Transactions on Fuzzy Systems
Impulsive effects on weak projective synchronization of parameter mismatched stochastic memristive neural networks
Journal of the Franklin Institute
Abstract This paper analyses the weak projective synchronization (WPS) of the parameter mismatche... more Abstract This paper analyses the weak projective synchronization (WPS) of the parameter mismatched memristive neural networks (MNNs) with stochastic disturbance and time delays via impulsive control. Complete synchronization cannot achieve because of the projective factor and mismatched parameters. Therefore, the WPS of practical MNNs under impulsive control strategy is studied. The augmented systems are built to utilize more information of the system and reduce the constraint conditions. Meanwhile, two types of comparison principles are used owing to the impulsive controller with and without time delays. Then, sufficient criteria for the exponential convergence of systems are obtained under the positive and negative effects of impulses. Finally, the validity of the theoretical results is verified by simulations of different conditions.
Extended Robust Exponential Stability of Fuzzy Switched Memristive Inertial Neural Networks With Time-Varying Delays on Mode-Dependent Destabilizing Impulsive Control Protocol
IEEE Transactions on Neural Networks and Learning Systems
This article investigates the problem of robust exponential stability of fuzzy switched memristiv... more This article investigates the problem of robust exponential stability of fuzzy switched memristive inertial neural networks (FSMINNs) with time-varying delays on mode-dependent destabilizing impulsive control protocol. The memristive model presented here is treated as a switched system rather than employing the theory of differential inclusion and set-value map. To optimize the robust exponentially stable process and reduce the cost of time, hybrid mode-dependent destabilizing impulsive and adaptive feedback controllers are simultaneously applied to stabilize FSMINNs. In the new model, the multiple impulsive effects exist between two switched modes, and the multiple switched effects may also occur between two impulsive instants. Based on switched analysis techniques, the Takagi–Sugeno (T-S) fuzzy method, and the average dwell time, extended robust exponential stability conditions are derived. Finally, simulation is provided to illustrate the effectiveness of the results.
Relaxed Exponential Stabilization for Coupled Memristive Neural Networks With Connection Fault and Multiple Delays via Optimized Elastic Event-Triggered Mechanism
IEEE Transactions on Neural Networks and Learning Systems
This article investigates the problem of relaxed exponential stabilization for coupled memristive... more This article investigates the problem of relaxed exponential stabilization for coupled memristive neural networks (CMNNs) with connection fault and multiple delays via an optimized elastic event-triggered mechanism (OEEM). The connection fault of the two or some nodes can result in the connection fault of other nodes and cause iterative faults in the CMNNs. Therefore, the method of backup resources is considered to improve the fault-tolerant capability and survivability of the CMNNs. In order to improve the robustness of the event-triggered mechanism and enhance the ability of the event-triggered mechanism to process noise signals, the time-varying bounded noise threshold matrices, time-varying decreased exponential threshold functions, and adaptive functions are simultaneously introduced to design the OEEM. In addition, the appropriate Lyapunov-Krasovskii functionals (LKFs) with some improved delay-product-type terms are constructed, and the relaxed exponential stabilization and globally uniformly ultimately bounded (GUUB) conditions are derived for the CMNNs with connection fault and multiple delays by means of some inequality processing techniques. Finally, two numerical examples are provided to illustrate the effectiveness of the results.
Uploads
Papers by Xiangxiang Wang