This paper proposes a novel motion controller for autonomous underwater vehicle based on parallel neural network. The motion controller consists of a real-time part, a self-learning part and a desired state programming part, and it is different from normal adaptive neural network controller in structure. Owing to the introduction of the self-learning part, on-line learning can be performed with...

 An adaptive input-output linearization method for general nonlinear systems is developed without using states of the system. Another key feature of this structure is the fact that, it does not need model of the system. In this scheme, neurolinearizer has few weights, so it is practical in adaptive situations.  Online training of neuroline...

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate currently QNN do not outperform classical DCNN (Deep Convo...

This thesis addresses two neural network based control systems. The first is a neural network based predictive controller. System identification and controller design are discussed. The second is a direct neural network controller. Parameter choice and training methods are discussed. Both controllers are tested on two different plants. Problems regarding implementations are discussed. First the...

Based on direct quaternion method, this paper explores the finite-time adaptive synchronization (FAS) of fractional-order delayed quaternion-valued fuzzy neural networks (FODQVFNNs). Firstly, a useful fractional differential inequality is created, which offers an effective way to investigate FAS. Then two novel control strategies are designed. By means our newly proposed inequality, basic knowl...

An adaptive neural network control scheme for thermal power system is described. No off-line training is required for the proposed neural network controller. The online tuning algorithm and neural network architecture are described. The performance of the controller is illustrated via simulation for different changes in process parameters. Performance of neural network controller is compared wi...

The paper presents a direct adaptive tracking control scheme for a class of matched SISO affine nonlinear uncertain systems with zero dynamic using neural network. Through neural network approximation, neural network is used as the emulator of the unknown ideal controller. A quadratic cost function of the error between the unknown ideal controller and the used neural network controller is minim...