This is code that will encompany an article that will appear in a special edition of a German IT magazine. The article is about explaining black-box machine learning models. In that article I’m showcasing three practical examples: Explaining supervised classification models built on tabular data using caret and the iml package Explaining image classification models with keras and lime Explaining text classification models with xgboost and lime

Continue reading

This is code that will encompany an article that will appear in a special edition of a German IT magazine. The article is about explaining black-box machine learning models. In that article I’m showcasing three practical examples: Explaining supervised classification models built on tabular data using caret and the iml package Explaining image classification models with keras and lime Explaining text classification models with xgboost and lime

Continue reading

On April 12th, 2018 I gave a talk about Explaining complex machine learning models with LIME at the Hamburg Data Science Meetup - so if you’re intersted: the slides can be found here: https://www.slideshare.net/ShirinGlander/hh-data-science-meetup-explaining-complex-machine-learning-models-with-lime-94218890 Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria.

Continue reading

On Wednesday, April 25th 2018 I am going to talk about explainability of machine learning models at the Minds Mastering Machines conference in Cologne. The conference will be in German, though. ERKLÄRBARKEIT VON MACHINE LEARNING: WIE KÖNNEN WIR VERTRAUEN IN KOMPLEXE MODELLE SCHAFFEN? Mit Machine-Learning getroffene Entscheidungen sind inhärent schwierig – wenn nicht gar unmöglich – nachzuvollziehen. Die Komplexität einiger der besten Modelle, wie Neuronale Netzwerke, ist genau das, was sie so erfolgreich macht.

Continue reading

I have written another blogpost about Looking beyond accuracy to improve trust in machine learning at my company codecentric’s blog: Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria. Why a model makes the predictions it makes, however, is generally neglected.

Continue reading

Slides from Münster Data Science Meetup These are my slides from the Münster Data Science Meetup on December 12th, 2017. knitr::include_url("https://shiring.github.io/netlify_images/lime_meetup_slides_wvsh6s.pdf") My sketchnotes were collected from these two podcasts: https://twimlai.com/twiml-talk-7-carlos-guestrin-explaining-predictions-machine-learning-models/ https://dataskeptic.com/blog/episodes/2016/trusting-machine-learning-models-with-lime Sketchnotes: TWiML Talk #7 with Carlos Guestrin – Explaining the Predictions of Machine Learning Models & Data Skeptic Podcast - Trusting Machine Learning Models with Lime Example Code the following libraries were loaded: library(tidyverse) # for tidy data analysis library(farff) # for reading arff file library(missForest) # for imputing missing values library(dummies) # for creating dummy variables library(caret) # for modeling library(lime) # for explaining predictions Data The Chronic Kidney Disease dataset was downloaded from UC Irvine’s Machine Learning repository: http://archive.

Continue reading