ABSTRACT The present paper aims to extend the potential learning method to overcome the problem of collective interpretation, which aims to interpret multi-layered neural networks by compressing them into the simplest ones. In the process of compression, positive, negative, and complicated weights have had unfavourable effects for interpretation. To deal with the problems of collective interpretation, the potential learning is extended only to use positive weights. In addition, to obtain more appropriate weights for interpretation, the number of candidate weights for higher potentialities is first increased as much as possible. Then, from among many candidates, more appropriate weights are selected as more important ones. This extended potentiality learning is expected to produce more stable and more simple representations for easy interpretation. The extended method was applied to three datasets, namely, an artificial dataset, a real eye-tracking dataset, and a student evaluation dataset. In all cases, it was observed that the selectivity of connection weights could be increased. Correspondingly, the majority of connection weights became positive, and the collective weights were quite similar to the regression coefficients of the logistic regression analysis. Finally, for the third dataset (student evaluations), the extended method could extract more explicit input-output relations, compared with the logistic regression analysis, while improving generalisation performance.

中文翻译：

---

通过多层神经网络的扩展潜力同化改进集体解释

摘要本文旨在扩展潜在学习方法以克服集体解释的问题，该方法旨在通过将多层神经网络压缩成最简单的神经网络来解释它们。在压缩过程中，正、负、复杂的权重都对解释产生了不利的影响。为了处理集体解释的问题，潜在的学习被扩展到仅使用正权重。此外，为了获得更合适的解释权重，首先尽可能多地增加更高潜力的候选权重的数量。然后，从众多候选中，选择更合适的权重作为更重要的权重。这种扩展的潜力学习有望产生更稳定、更简单的表示，以便于解释。将扩展方法应用于三个数据集，即人工数据集、真实眼动追踪数据集和学生评价数据集。在所有情况下，都观察到可以增加连接权重的选择性。相应地，大多数连接权重变为正，并且集合权重与逻辑回归分析的回归系数非常相似。最后，对于第三个数据集（学生评价），与逻辑回归分析相比，扩展方法可以提取更明确的输入-输出关系，同时提高泛化性能。据观察，可以增加连接权重的选择性。相应地，大多数连接权重变为正，并且集合权重与逻辑回归分析的回归系数非常相似。最后，对于第三个数据集（学生评价），与逻辑回归分析相比，扩展方法可以提取更明确的输入-输出关系，同时提高泛化性能。据观察，可以增加连接权重的选择性。相应地，大多数连接权重变为正，并且集合权重与逻辑回归分析的回归系数非常相似。最后，对于第三个数据集（学生评价），与逻辑回归分析相比，扩展方法可以提取更明确的输入-输出关系，同时提高泛化性能。