Merge pull request #45 from christophM/future

Future

README.md

@@ -51,9 +51,10 @@ All notable changes to the book will be documented here.
 - Added feature interaction chapter
 - Improved example in partial dependence plot chapter
 - The weights in LIME text chapter where shown with the wrong words. This has been fixed.
+- Improved introduction text
+- Added chapter about the future of interpretability
 - Added Criteria for Intepretability Methods
 
-
 ### v0.3 (2018-04-24)
 - Reworked the Feature Importance Chapter
 - Added third short story

manuscript/01-introduction.Rmd

@@ -1,24 +1,31 @@
 # Introduction {#intro}
 
 This book will teach you how to make (supervised) machine learning models interpretable.
-It contains one or the other mathematical formula, but it's kept at a manageable level of math.
-This book is not for people who are trying to learn machine learning from scratch.
+The chapters contain some mathematical formulas, but you should be able to understand the ideas behind the methods even without the mathematics.
+This book is not for people who try to learn machine learning from scratch.
 If you are new to machine learning, there are loads of books and other resources for learning the basics.
 I recommend the book [Elements of Statistical Learning](https://web.stanford.edu/~hastie/ElemStatLearn/) from Hastie, Tibshirani, and Friedman (2009) [^Hastie] and [Andrew Ng's "Machine Learning" online course on coursera](https://www.coursera.org/learn/machine-learning) to get started with machine learning.
-Both the book and the course are available for free!
+Both the book and the course are available free of charge!
+
+New methods for machine learning interpretability are published at breakneck speed.
+Keeping update with all of them would be madness and simply impossible. 
+That's why you won't find the most novel and shiny methods in this book, but rather the basic concepts of machine learning interpretability.
+These basics will prepare you well to make machine learning models interpretable.
+Internalizing the basic concepts also empowers you to better understand and evaluate any new paper on interpretability that has been published on [arxiv.org](arxiv.org) in the last 5 minutes since you began to read this book (I may be exaggerating).
 
-This book starts with some [short stories](#storytime), which are not required to understand the book, but hopefully entertaining!
+This book starts with some (dystopian) [short stories](#storytime), which are not needed to understand the book, but hopefully are entertaining!
 Then the book explores the concepts of [machine learning interpretability](#interpretability):
-It reveals when interpretability is important and discusses different types of explanations.
-Definitions used throughout the book can be [looked up](#definitions).
-All models and methods are explained and demonstrated with real data examples [described here](#data).
-One way to make machine learning interpretable is by using [interpretable models](#simple), like linear models or decision trees.
-The other option is to use [model-agnostic interpretability methods](#agnostic).
+It shows when interpretability is important and discusses different types of explanations.
+Definitions used throughout the book can be [looked up here](#definitions).
+Most of the models and methods explained are presented using real data examples [described here](#data).
+One way to make machine learning interpretable is to use [interpretable models](#simple), like linear models or decision trees.
+The other option is the use [model-agnostic interpretation tools](#agnostic), that can be applied to any supervised machine learning model.
 The model-agnostic chapter covers methods like partial dependence plots and permutation feature importance.
 Model-agnostic methods work by changing the input of the machine learning model and measuring changes in the output.
+Finish the book with an optimistic outlook on what [the future of interpretable machine learning](#future) might look like.
 
-You can either read the book from start to end or directly jump to the methods you are interested in.
+You can either read the book from beginning to end or jump directly to the methods that interest you.
 I hope you will enjoy the read!
 
 
-[^Hastie]: Hastie, T, R Tibshirani, and J Friedman. 2009. The elements of statistical learning. http://link.springer.com/content/pdf/10.1007/978-0-387-84858-7.pdf.
+[^Hastie]: Hastie, T, R Tibshirani, and J Friedman. 2009. The elements of statistical learning. http://link.springer.com/content/pdf/10.1007/978-0-387-84858-7.pdf.

manuscript/02-interpretability.Rmd

@@ -5,6 +5,7 @@ devtools::load_all("../")
 # Interpretability {#interpretability}
 
 Throughout the book, I will use this rather simple, yet elegant definition of interpretability from  Miller (2017) [^Miller2017] : **Interpretability is the degree to which a human can understand the cause of a decision.**
+Another take is: **Interpretability is the degree to which a human can consistently predict the model's result**.
 The higher the interpretability of a model, the easier it is for someone to comprehend why certain decisions (read: predictions) were made.
 A model has better interpretability than another model, if its decisions are easier to comprehend for a human than decisions from the second model.
 I will be using both the terms interpretable and explainable equally.