与传统人工神经网络的算法相比,覆盖算法有运行速度快、精度高和易于理解的优点,但是覆盖算法的学习顺序是随机选择的,大量实验表明样本的学习顺序对神经网络的性能有着显著的影响.基于竞争的覆盖算法是在覆盖算法的基础上提出的,以消除算法中学习顺序所产生的影响.在该算法中,通过加入竞争机制,神经网络在学习样本的同时会逐步调整覆盖中心以形成更优的覆盖域.实验表明改进后的覆盖算法可以有效减少覆盖数量,减少拒识样本数,提高识别精度.%Compared with traditional neural networks, covering algorithm possesses some advantages, such as running fast, high accuracy and easy to understand, but the learning order of covering algorithm is randomly selected. Experiments show that the learning sequence has a significant impact on the network performance. It proposes a new kind of algorithm named covering algorithm based on competition. In this algorithm, sphere domains can be adjusted gradually. Experiments show that this algorithm can effectively reduce the number of sphere domains, decrease the number of rejected samples and improve the recognition accuracy.
展开▼
