Representation and generalization properties of class-entropy networks
Representation and generalization properties of class-entropy networks
复制标题
类熵网络的表示和泛化特性
DOI：
10.1109/72.737491
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
R. Zunino
中科院分区：
文献类型：
--
作者：
S. Ridella;S. Rovetta;R. Zunino
使用条件类熵（CCE）作为成本函数允许前馈网络充分利用分类相关信息。基于CCE的网络将数据空间划分为分区，分区被分配明确的符号并由类别信息标记。通过这种标记机制，网络可以在局部层面上对经验数据分布进行建模。区域标记随着网络训练过程而发展，该过程遵循塑性算法。本文证明了基于CCE的网络性能的几个理论性质，并考虑了训练过程中的收敛性和运行时的泛化能力。此外，分析标准和实用程序提出了提高训练网络的泛化性能。人工和真实世界领域的实验证实了这类网络的准确性，并证明了所描述的方法的有效性。
Using conditional class entropy (CCE) as a cost function allows feedforward networks to fully exploit classification-relevant information. CCE-based networks arrange the data space into partitions, which are assigned unambiguous symbols and are labeled by class information. By this labeling mechanism the network can model the empirical data distribution at the local level. Region labeling evolves with the network-training process, which follows a plastic algorithm. The paper proves several theoretical properties about the performance of CCE-based networks, and considers both convergence during training and generalization ability at run-time. In addition, analytical criteria and practical procedures are proposed to enhance the generalization performance of the trained networks. Experiments on artificial and real-world domains confirm the accuracy of this class of networks and witness the validity of the described methods.