基于带偏差递归神经网络蛋白质关联图的预测

Prediction of Protein Contact Map Based on Deviation Units Recurrence Neural Network

针对BP神经网络在学习速度方面的不足,在Jordan和Elman网络结构的基础上,提出一种带偏差单元的递归网络模型,根据BP算法推导出该网络模型的权系数调整规则,并应用该网络模型进行了蛋白质关联图预测的仿真分析.结果表明,该网络模型的收敛速度比一般BP网络有很大提高,具有一定的实用性.

To deal with the weakness of the BP neural network in learning speed, an Deviation Units Recurrence Neural Network model is presented based on the Jordan and Elman neural network. The weight-regulating method is developed based on BP algorithm. Simulations on fault diagnosis were performed with this neural network model. Experimental results show that the converging speed of this network model is faster than that of the traditional BP network and this model has a good practicability.