书籍《Interpretable Machine Learning》的学习笔记

本书链接:https://christophm.github.io/interpretable-ml-book/
以下目录为书中的目录。

2.3 Scope of Interpretability

2.3.1 Algorithm Transparency(算法透明度)

算法透明度是关于算法如何从数据中学习到一个模型以及它可以学习到的关系。算法透明度仅需要算法知识,而无需数据或学习模型。本书将关注于模型可解释性(model interpretability)而不是算法透明度。
线性模型的最小二乘法等算法已得到很好的研究和理解,但深度学习方法的理解则较少,因此深度学习方法被认为不那么透明。

2.3.2 Global, Holistic Model Interpretability(全局整体模型可解释性)
训练的模型如何做出预测?

2.3.3 Global Model Interpretability on a Modular Level(模块化级别的全局模型可解释性)
模型的各个部分如何影响预测?

2.3.4 Local Interpretability for a Single Prediction(单个预测的局部可解释性)
模型为何对实例做出确定的预测?
当仅关注于一个特定实例(样本)时,原本复杂的模型也许会表现出更简洁的行为。
就局部而言,预测可能仅线性或单调依赖于某些特征,而不是对它们的复杂依赖。

2.3.5 Local Interpretability for a Group of Predictions(一组预测的局部可解释性)
模型为何对一组实例做出特定的预测?
Model predictions for multiple instances can be explained either with global model interpretation methods (on a modular level) or with explanations of individual instances.
译文:可以使用全局模型解释方法(在模块级别)或单个实例的解释来解释多个实例的模型预测。

2.4 Evaluation of Interpretability

Doshi-Velez和Kim(2017)为评估可解释性提出了三个主要层次:

  1. Application level evaluation (real task):将说明放入产品中,并由最终用户进行测试;
  2. Human level evaluation (simple task) :人类水平的评估是一种简化的应用水平评估,主要是让外行来对解释进行评估,让其选择他认为最好的;
  3. Function level evaluation (proxy task):这种方法不需要人类参与,主要是在一些模型已经被其他人在人类水平进行评估后进行使用。
pdf书签没有链接正确,本人对此进行了修正 Paperback: 454 pages Publisher: Packt Publishing - ebooks Account (September 2015) Language: English ISBN-10: 1783555130 ISBN-13: 978-1783555130 Unlock deeper insights into Machine Leaning with this vital guide to cutting-edge predictive analytics About This Book Leverage Python's most powerful open-source libraries for deep learning, data wrangling, and data visualization Learn effective strategies and best practices to improve and optimize machine learning systems and algorithms Ask and answer tough questions of your data with robust statistical models, built for a range of datasets Who This Book Is For If you want to find out how to use Python to start answering critical questions of your data, pick up Python Machine Learning whether you want to get started from scratch or want to extend your data science knowledge, this is an essential and unmissable resource. What You Will Learn Explore how to use different machine learning models to ask different questions of your data Learn how to build neural networks using Keras and Theano Find out how to write clean and elegant Python code that will optimize the strength of your algorithms Discover how to embed your machine learning model in a web application for increased accessibility Predict continuous target outcomes using regression analysis Uncover hidden patterns and structures in data with clustering Organize data using effective pre-processing techniques Get to grips with sentiment analysis to delve deeper into textual and social media data
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值