一种基于广义子波基函数选择的智能化神经元集聚模型

An Application-Oriented Intelligent Neurons Assemblage Model Based on Generalized Wavelet Basis Function

针对神经网络中传统神经元模型在结构和信息存储能力上存在的不足，提出了一种基于广义子波基函数网络的神经元集聚模型。在对一类非线性函数的逼近中，与传统的神经元模型相比，新模型不仅收敛速度极快，非线性逼近能力更好，而且还使神经网络具有了内部结构变尺度自适应调整和广义信息存储等智能化特点，更符合生物原型的实际情况。仿真实验验证了新模型方案在此类函数逼近问题中应用的可行性和高效性，从而为智能化神经网络的设计提供了一种新的思路和方法。

In undertaking a research and development project, we found that neuron model is inadequate owing to its defects such as those inherent in its structure and in its capability of information storage. So we propose an intelligent neurons assemb1age model with generalized wavelet basis function network as its excited function. After careful study of the place structure of functional distribution and of the changes of states of neurons, we introduce the concept of network inlays into the new model and we use a good partial character and a good variable - scale one in this new model- Compared with neuron model, the new model's convergence rate is much faster and its nonlinear approach capabillty is much better. The intelligent characters, such as the variable - scale adaptive adjustment of structure and the generalized information storage, make the new model reflect much more faithfully the biological original. Finally, simulation results, as shown in Figs. 3 through 5 and as given in Table 1,indicate preliminarily that our new model is feasible.