基于粗神经网络的企业组织创新风险预警

提出了基于粗神经网络的企业组织创新风险预警模型,通过粗集减少属性的数量,提取主要的特征属性,降低神经网络构成系统的复杂性及计算时间;结合神经网络系统的容错能力、并行处理能力、抗干扰能力及处理非线性问题能力,将粗集与神经网络进行串行结合.实例研究表明,将Rough Set与BP神经网络结合起来应用于企业组织创新风险预警,大大简化了BPNN的结构,减少了网络的计算量,加快了收敛速度.

A Metod for Risk Early-warming of Enterprise Organizational Innovation Based on Rough Set and Neural Network

This article proposed the risk early warning model of organizational innovation based on Rough Set and Neural Network. Through the Rough set the total attribute quantity could be reduced, the main characteristic attributes were withdrawn, the complexity of Neural Network system and the computing time were reduced, too; Combined with the abilities of the union nerve network system fault-tolerant ability, the parallel processing ability, the antijamming ability and the processing non-linear problem ability, carries on the Rough set in the Neural Network the serial union. The example research indicates, unifies Rough Set and the BP Neural Network applies to the organizational innovation risk early warning, greatly simplified the BPNN structure, reduced the network computation quantity, sped up the convergence rate.