arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.17002cs.LG
收藏

条件自回归是可解释的分类器

Conditional Autoregressors are Interpretable Classifiers

Australian National University(澳大利亚国立大学)

Nathan Elazar

摘要:

我们探索使用类条件自回归(CA)模型进行图像分类MNIST-10。自回归模型通过组合来自每个单独特征的概率来将概率分配给整个输入;因此CA所做的分类决策可以很容易地分解为每个输入特征的贡献。也就是说,CA本质上是局部可解释的。我们的实验表明,与标准分类器相比,天真地训练CA的准确率要差得多,但这是由于过度拟合而不是缺乏表达能力。使用来自标准分类器的知识蒸馏,可以训练学生CA以匹配教师的表现,同时仍然是可解释的。

英文摘要:

We explore the use of class-conditional autoregressive (CA) models to perform image classification on MNIST-10. Autoregressive models assign probability to an entire input by combining probabilities from each individual feature; hence classification decisions made by a CA can be readily decomposed into contributions from each each input feature. That is to say, CA are inherently locally interpretable. Our experiments show that naively training a CA achieves much worse accuracy compared to a standard classifier, however this is due to over-fitting and not a lack of expressive power. Using knowledge distillation from a standard classifier, a student CA can be trained to match the performance of the teacher while still being interpretable.

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。

↑