The Institute for Ethical AI & Machine Learning

THE ML ENGINEER 🤖 Issue #62

This week in Issue #62:   Jurgen's Retrospective AI 2010s Missinformation in a Hyperconnected World MLOps: The End of End-to-End Empirical Quality Metrics for Deep Learning How to Interpret an ML Model Featured OSS Production ML Libraries Awesome AI Guidelines to check out this week + more 🚀   Forward the email, or share the online version on 🐦 Twitter,  💼 Linkedin and  📕 Facebook!   If you would like to suggest articles, ideas, papers, libraries, jobs, events or provide feedback just hit reply or send us an email to a@ethical.institute! We have received a lot of great suggestions in the past, thank you very much for everyone's support!

Jurgen's Retrospective AI 2010s Jürgen Schmidhuber has put together a fantasic post focusing on the recent decade's most important developments and applications based on their work, as well as developments from related work, addressing privacy and data markets. The post includes LSTMs, Feed Forward NNs, Network Comparisons, Trends and the Future.

Hyperconnected Missinformation This Friday we are organising an open event in London to dive into the topic of missinformation and bias in a hyperconnected world. Head of Machine Learning at Factmata Dr. Magdalena Lis will be presenting a brief overview of the topic of fake news and bias, which will follow by a discourse on this topic to explore key themes, such as "Is social media fuelling the spread of misinformation?", "what can be done to address it?". Come join us!

MLOps: The End of End-to-End Mosaic has put together an overview of the concept of MLOps in the context of the full lifecycle of machine learning. This post provides a conceptual understanding of the different stages in end-to-end ML including data exploration, modelling and production inference.

How to Interpret an ML Model A practical jupyter notebook that dives into some high level techniques for explaining machine learning models. Some of the methods explored include partial dependency plots, individual conditional expectation, tree ensambles feature contribution, permutation feature importance and the good old LIME & SHAP.

Empirical Quality Metrics for DL A blog post that dives into the release of a tool called "Weightwatcher" which provides a set of tools for computing quality metrics of trained and pre-trained deep neural networks. The post provides insihgt on some of the metrics that are computed, as well as ways in which models can be benchmarked against each other.

OSS: Adversarial Robustness   The topic for this week's featured production machine learning libraries is Adversarial Robustness. We are currently looking for more libraries to add - if you know of any that are not listed, please let us know or feel free to add a PR. The four featured libraries this week are: Alibi Detect - alibi-detect is a Python package focused on outlier, adversarial and concept drift detection. The package aims to cover both online and offline detectors for tabular data, text, images and time series. The outlier detection methods should allow the user to identify global, contextual and collective outliers. CleverHans - library for testing adversarial attacks / defenses maintained by some of the most important names in adversarial ML, namely Ian Goodfellow (ex-Google Brain, now Apple) and Nicolas Papernot (Google Brain). Comes with some nice tutorials! Foolbox - second biggest adversarial library. Has an even longer list of attacks - but no defenses or evaluation metrics. Geared more towards computer vision. Code easier to understand / modify than ART - also better for exploring blackbox attacks on surrogate models. AdvBox - generate adversarial examples from the command line with 0 coding using PaddlePaddle, PyTorch, Caffe2, MxNet, Keras, and TensorFlow. Includes 10 attacks and also 6 defenses. Used to implement StealthTshirt at DEFCON!   If you know of any libraries that are not in the "Awesome MLOps" list, please do give us a heads up or feel free to add a pull request!

OSS: Awesome AI Guidelines   As AI systems become more prevalent in society, we face bigger and tougher societal challenges. We have seen a large number of resources that aim to takle thiese challenges in the form of AI Guidelines, Principles, Ethics Frameworks, etc, however there are so many resources it is hard to navigate. Because of this we started an Open Source initiative that aims to map the ecosystem to make it simpler to navigate. We will be showcasingitg three resources from our list so we can check them out every week. This week's resources are: AI & Machine Learning 8 principles for Responsible ML - The Institute for Ethical AI & Machine Learning has put together 8 principles for responsible machine learning that are to be adopted by individuals and delivery teams designing, building and operating machine learning systems An Evaluation of Guidelines - The Ethics of Ethics; A research paper that analyses multiple Ethics principles ACM's Code of Ethics and Professional Conduct - This is the code of ethics that has been put together in 1992 by the Association for Computer Machinery and updated in 2018 From What to How - An initial review of publicly available AI Ethics Tools, Methods and Research to translate principles into practices   If you know of any guidelines that are not in the "Awesome AI Guidelines" list, please do give us a heads up or feel free to add a pull request!

© 2018 The Institute for Ethical AI & Machine Learning