一种具备识别结果解释能力的AI架构
An AI Architecture with the Capability to Explain Recognition Results
AI总结：
针对现有可解释AI方法解释性不足或性能不及不可解释模型的问题，提出结合可解释与不可解释流并引入新可解释性指标、对比神经网络经典评估指标并提出最优新指标的两种方法，提升了可解释系统的性能。
摘要：
可解释性是建立对机器学习结果信心的必要条件。部分可解释方法采用事后（post hoc）方法解释机器学习模型的权重，另一些则突出输入中对决策有贡献的区域。这些方法未能用通俗语言充分解释决策。基于属性的可解释系统已被证明能提供通俗语言的解释，但它们的性能不及领先的不可解释机器学习方法。本研究聚焦于指标对可解释性的重要性，提出了两种可提升性能的方法。第一种方法引入可解释流与不可解释流的组合，提出一种表征决策可解释性的指标。第二种方法比较了评估系统中神经网络有效性的经典指标，提出一种性能最优的新指标。本文展示了新方法的结果以及来自手写数据集的示例。
英文摘要：
Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to decisions. These methods do not adequately explain decisions, in plain terms. Explainable property-based systems have been shown to provide explanations in plain terms, however, they have not performed as well as leading unexplainable machine learning methods. This research focuses on the importance of metrics to explainability and contributes two methods yielding performance gains. The first method introduces a combination of explainable and unexplainable flows, proposing a metric to characterize explainability of a decision. The second method compares classic metrics for estimating the effectiveness of neural networks in the system, posing a new metric as the leading performer. Results from the new methods and examples from handwritten datasets are presented.
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。
