Setiono R
Department of Information Systems and Computer Science, National University of Singapore, Kent Ridge, Republic of Singapore.
Neural Comput. 1997 Jan 1;9(1):205-25. doi: 10.1162/neco.1997.9.1.205.
An algorithm for extracting rules from a standard three-layer feedforward neural network is proposed. The trained network is first pruned not only to remove redundant connections in the network but, more important, to detect the relevant inputs. The algorithm generates rules from the pruned network by considering only a small number of activation values at the hidden units. If the number of inputs connected to a hidden unit is sufficiently small, then rules that describe how each of its activation values is obtained can be readily generated. Otherwise the hidden unit will be split and treated as output units, with each output unit corresponding to an activation value. A hidden layer is inserted and a new subnetwork is formed, trained, and pruned. This process is repeated until every hidden unit in the network has a relatively small number of input units connected to it. Examples on how the proposed algorithm works are shown using real-world data arising from molecular biology and signal processing. Our results show that for these complex problems, the algorithm can extract reasonably compact rule sets that have high predictive accuracy rates.
提出了一种从标准三层前馈神经网络中提取规则的算法。首先对训练好的网络进行剪枝，不仅要去除网络中的冗余连接，更重要的是要检测相关输入。该算法通过仅考虑隐藏单元处的少量激活值，从剪枝后的网络中生成规则。如果连接到一个隐藏单元的输入数量足够少，那么就可以很容易地生成描述其每个激活值如何获得的规则。否则，该隐藏单元将被拆分并视为输出单元，每个输出单元对应一个激活值。插入一个隐藏层并形成一个新的子网，进行训练和剪枝。重复这个过程，直到网络中的每个隐藏单元都有相对较少的输入单元连接到它。使用分子生物学和信号处理中的实际数据展示了所提出算法的工作方式示例。我们的结果表明，对于这些复杂问题，该算法可以提取出具有较高预测准确率的合理紧凑的规则集。
