摘要： 神经网络的学习算法通常是采用梯度下降法，此方法容易陷入局部极小而得到次最优解。另外，对于有些应用来说，用于训练网络的样本的输入/输出数据无法精确给出，而只能以一定的范围的形式给出，这就给传统的神经网络带来了困难。该文提出了一种基于区间优化的神经网络学习算法，可以很好地解决上面所提到的传统神经网络学习算法的缺点。

关键词: 神经网络；学习算法；区间算法；全局优化

Abstract: Neural networks are usually trained using local gradient-based procedures. Such methods are frequently found sub-optimal solutions being trapped in local minima. In solving some application problems, the input/output data sets used to train a neural network may not be hundred percent precise but within certain range. It is difficult for the traditional neural network to solve such problems. A learning algorithm based on interval optimization is presented in this paper. The above disadvantages of the traditional learning algorithm are settled by using this method

Key words: Neural network; Learning algorithm; Interval arithmetic; Global optimization