Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems
Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems
复制标题
DOI：
10.1007/s11063-011-9207-8
复制
发表时间：
2012-04-01
影响因子：
3.1
通讯作者：
Kathirvalavakumar, T.
中科院分区：
文献类型：
--
作者：
Augasta, M. Gethsiyal;Kathirvalavakumar, T.
人工神经网络通常具有很高的分类准确率，但由于缺乏解释能力，它们被认为是黑箱。本文提出了新的规则提取算法RxREN来克服这个缺点。在教学方法中，该算法从训练好的神经网络中提取混合模式属性数据集的规则。该算法依靠逆向工程技术来修剪不重要的输入神经元，并发现神经网络的每个重要输入神经元在分类中的技术原理。该算法的新奇在于提取规则的简单性和规则中的条件同时包含离散和连续属性模式。在虹膜、白细胞、肝炎、pid、电离层和creditg等6个真实的数据集上的实验表明，该算法比其他神经网络规则提取方法具有更高的分类精度和更小的规则集提取效率。
Artificial neural networks often achieve high classification accuracy rates, but they are considered as black boxes due to their lack of explanation capability. This paper proposes the new rule extraction algorithm RxREN to overcome this drawback. In pedagogical approach the proposed algorithm extracts the rules from trained neural networks for datasets with mixed mode attributes. The algorithm relies on reverse engineering technique to prune the insignificant input neurons and to discover the technological principles of each significant input neuron of neural network in classification. The novelty of this algorithm lies in the simplicity of the extracted rules and conditions in rule are involving both discrete and continuous mode of attributes. Experimentation using six different real datasets namely iris, wbc, hepatitis, pid, ionosphere and creditg show that the proposed algorithm is quite efficient in extracting smallest set of rules with high classification accuracy than those generated by other neural network rule extraction methods.