ankitbit/MAGMIL

This repository contains code, information and datasets for the project on making interpretable models titled "Model Agnostic Methods for Interpretable Machine Learning". The abstract can be accessed at https://docs.google.com/document/d/1k2-beHD4YQxXpH8ExUM2Gd-yE5VqdluhiCsUIO3czRM/edit?usp=sharing

Model Agnostic Methods for Interpretable Machine Learning

European Union’s new General Data Protection Regulation which is going to be enforced beginning from 25th of May, 2018 will have potential impact on the routine use of machine learning algorithms by restricting automated individual decision-making (that is, algorithms that make decisions based on user-level predictors) which ”significantly affect” users. The law will also effectively create a ”right to explanation,” whereby a user can ask for an explanation of an algorithmic decision that was made about them. Considering such challenging norms on the use of machine learning systems, we are making an attempt to make the models more interpretable. While we are concerned about developing a deeper understanding of decisions made by a machine learning model, the idea of extracting the explaintations from the machine learning system, also known as model-agnostic interpretability methods has some benefits over techniques such as model specific interpretability methods in terms of flexibility. Similarly, the idea of using only interpetable models has some drawbacks in terms of accuracy. In this study, we will try to study the application of model agnostic interpretability methods for making highly complex black box methods more interpretable. Some aspects of the model agnostic explanation systems such as model flexibility, explanation flexibility and representation flexibility will also be examined.

References-

• Practical Techniques for Interpreting Machine Learning Models: Introductory Open Source Examples Using Python, H2O, and XGBoost

• Machine Learning Interpretability

• A Unified Approach to Interpreting Model Predictions

• Anchors- High Precision Model Agnostic Explanations

Welcome to GitHub Pages

You can use the editor on GitHub to maintain and preview the content for your website in Markdown files.

Whenever you commit to this repository, GitHub Pages will run Jekyll to rebuild the pages in your site, from the content in your Markdown files.

Markdown

Markdown is a lightweight and easy-to-use syntax for styling your writing. It includes conventions for

Syntax highlighted code block

# Header 1
## Header 2
### Header 3

- Bulleted
- List

1. Numbered
2. List

**Bold** and _Italic_ and `Code` text

[Link](url) and ![Image](src)

For more details see GitHub Flavored Markdown.

Jekyll Themes

Your Pages site will use the layout and styles from the Jekyll theme you have selected in your repository settings. The name of this theme is saved in the Jekyll _config.yml configuration file.

Support or Contact

Having trouble with Pages? Check out our documentation or contact support and we’ll help you sort it out.