• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual conference on Neural Information Processing Systems >Examples are not Enough, Learn to Criticize! Criticism for Interpretability
【24h】

Examples are not Enough, Learn to Criticize! Criticism for Interpretability

机译：例子还不够，要学会批评！对可解释性的批评

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the complexity. In order for users to construct better mental models and understand complex data distributions, we also need criticism to explain what are not captured by prototypes. Motivated by the Bayesian model criticism framework, we develop MMD-critic which efficiently learns prototypes and criticism, designed to aid human interpretability. A human subject pilot study shows that the MMD-critic selects prototypes and criticism that are useful to facilitate human understanding and reasoning. We also evaluate the prototypes selected by MMD-critic via a nearest prototype classifier, showing competitive performance compared to baselines.
机译：在提高高度复杂分布的可解释性的过程中，广泛使用基于示例的解释。但是，仅凭原型很少能代表复杂性的要点。为了使用户能够构建更好的思维模型并理解复杂的数据分布，我们还需要批评以解释原型未捕获的内容。在贝叶斯模型批评框架的激励下，我们开发了MMD-critic，该模型可以有效地学习原型和批评，旨在帮助人们理解。一项人类主题试验研究表明，MMD批评家选择了有助于促进人类理解和推理的原型和批评。我们还通过最近的原型分类器评估了MMD-critic选择的原型，与基线相比，它们具有竞争优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号