arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.12271cs.LGcs.AI
收藏

NN2Rules:从神经网络中提取规则表

NN2Rules: Extracting Rule List from Neural Networks

LinkedIn AI(领英人工智能)

G Roshan Lal, Varun Mithal

摘要:

我们提出了一个算法,NN2Rules,将一个训练好的神经网络转换成一个规则列表。规则列表更容易解释,因为它们更符合人类做出决策的方式。NN2Rules是一种规则提取的分解方法,即,它从训练好的神经网络模型的参数中提取一组决策规则。我们表明,提取的决策规则具有相同的预测作为神经网络的任何输入,因此,相同的精度。NN2Rules的一个关键贡献是它允许隐藏神经元行为是软二进制的(例如,sigmoid激活)或校正线性(ReLU),这与利用软二进制激活的假设开发的现有分解方法相反。

英文摘要:

We present an algorithm, NN2Rules, to convert a trained neural network into a rule list. Rule lists are more interpretable since they align better with the way humans make decisions. NN2Rules is a decompositional approach to rule extraction, i.e., it extracts a set of decision rules from the parameters of the trained neural network model. We show that the decision rules extracted have the same prediction as the neural network on any input presented to it, and hence the same accuracy. A key contribution of NN2Rules is that it allows hidden neuron behavior to be either soft-binary (eg. sigmoid activation) or rectified linear (ReLU) as opposed to existing decompositional approaches that were developed with the assumption of soft-binary activation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑