This paper proposes a discrete recurrent neural network model to implement winner-take-all function. This network model has simple organizations and clear dynamic behaviours. The dynamic properties of the proposed winner-take-all networks are studied in detail. Simulation results are given to show network performance. Since the network model is formulated as discrete time systems , it has advan...

This paper explores training and initialization aspects of dynamic neural networks when applied to the nonlinear system identification problem. A well known dynamic neural network structure contains both output states and hidden states. Output states are related to the outputs of the system represented by the network. Hidden states are particularly important in allowing dynamic neural networks ...

This paper proposes an intelligent approach for dynamic identification of the vehicles. The proposed approach is based on the data-driven identification and uses a high-performance local model network (LMN) for estimation of the vehicle’s longitudinal velocity, lateral acceleration and yaw rate. The proposed LMN requires no pre-defined standard vehicle model and uses measurement data to identif...

estimation (forecasting) of industrial production costs is one of the most important factor affecting decisions in the highly competitive markets. thus, accuracy of the estimation is highly desirable. hibrid regression neural network is an approach proposed in this paper to obtain better fitness in comparison with regression analysis and the neural network methods. comparing the estimated resul...

In order to forecast the stock market more accurately, according to the dynamic property for the stock market, propose the real time modeling forecast via dynamic recurrent neural network and use GA to study online, then it improves the network performance and better describes the dynamic characteristic of stock market. By forecasting Shanghai negotiable securities index, it shows better validi...

In this paper we present a new beat tracking algorithm which extends an existing state-of-the-art system with a multi-model approach to represent different music styles. The system uses multiple recurrent neural networks, which are specialised on certain musical styles, to estimate possible beat positions. It chooses the model with the most appropriate beat activation function for the input sig...

Dynamic neural network architectures can deal naturally with sequential data through recursive processing enabled by feedback connections. We show how such architectures are predisposed for suffix-based Markovian input sequence representations in both supervised and unsupervised learning scenarios. In particular, in the context of such architectural predispositions, we study computational and l...

Because of their parallelism, functional approXimation and learning capabilities, artificial neural networks can be effectively employed to apjmximate nonlinear functions, and to synthesize controllers for nonlinear dynamic systems. The use of dynamic neural networks to model and control dynamic systems is of great importance in the control paradigm. The intent of this paper is to use one such ...

For seismic resistant design of critical structures, a dynamic analysis, based on either response spectrum or time history is frequently required. Due to the lack of recorded data and randomness of earthquake ground motion that might be experienced by the structure under probable future earthquakes, it is usually difficult to obtain recorded data which fit the necessary parameters (e.g. soil ty...