The MachineLearning EngineerIssue #31

This week in Issue #31:

• End-to-end XAI in production
• Causal inference for UX
• ML in enterprise
• Adversarial Robustness
• The GANs story so far
• AI conferences
• ML jobs
• + 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!

End-to-end XAI in production

Our PyData London talk last week is now on youtube, where we spoke about end-to-end machine learning explainability techniques with an emphasis on production. During this talk we covered the tools and approaches you can take to tackle machine learning explainability in data and models. We also introduced the concept of production ML explainer design patterns which abstract the XAI techniques so they can use at scale across live models in production.

Causal inference to improve UX

Excellent and comprehensible post by Uber Engineering on how they use Causal Inference techniques to improve user experience. In this post they introduce the importance of the topic, as well as a deep dive on key causal inference techniques including: compiler average cuasal effect (CACE), CUPED / Diff-in-diff propensity score matching (IPTW), Heterogeneus treatment effect Uplift modeling, quantile regression and mediation modelling. An excellent post that covers the theoretical and practical perspectives of causal inference techniques.

Managing ML in enterprise

Excellent post by the O’Reilly team covering key lessons learned from the field from managing production machine learning systems in the financial and healthcare sectors. Historically these two sectors (and the financial sector in particular) tends to lead the way on technology adoption, so it’s often great to take some of the learnings obtained introducing innovations to the sector, and abstract them to help introduce innovations into other sectors (such as transport, energy, construction, etc).

Intro to Adversarial Examples

Great high level introduction on the topic of Adversarial Robustness, which provides an introduction to this topic, as well as case studies and examples that showcase the importance of this branch of techniques. The post breaks down evasion attacks into five separate classes: gradients, confidence scores, hard labels, surrogate models and brute force.

The GAN Story so far

Great article which provides a very comprehensible overview of the recent history of Generative Adversarial Networks. GANs, DCGANs, CGANs, CycleGANs, CoGANs, ProGANs, WGANs, SAGANs, BIgGANs and StyleGANS - GANS EVERYWHERE!

OSS: Adversarial Robustness

The theme for this week’s featured ML libraries is Adversarial Robustness, which includes tools for adversarial attacks and adversarial security. These libraries are an incredibly exciting addition that fall in our Responsible ML Principle #8, and the whole section was contributed by one of the Fellows at the Institute Ilja Moisejevs from Calipso AI. The four featured libraries this week are:

• 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.
• IBM Adversarial Robustness Toolbox (ART) - at the time of writing this is the most complete off-the-shelf resource for testing adversarial attacks and defenses. It includes a library of 15 attacks, 10 empirical defenses, and some nice evaluation metrics. Neural networks only.
• 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!

MLConf = Conferences & Events

We feature conferences that have core ML tracks (primarily in Europe for now) to help our community stay up to date with great events coming up.

Technical & Scientific Conferences

• EURNLP 2019 [11/10/2019] - European NLP Research summit in London, UK.

• Data Natives [21/11/2019] - Data conference in Berlin, Germany.

• ODSC Europe [19/11/2019] - The Open Data Science Conference in London, UK.

• EurNLP [11/10/2019] - Europe’s NLP research conference (pronounced “Your NLP”) in London, UK

• Khipu AI [11/11/2019] - Latin American Meeting in Artifical Intelligence in Montevideo, Uruguay.

Business Conferences

• Predictive Analytics World [18/11/2019] - Conference for Business AI in Berlin, Germany.

• Big Data LDN 2019 [13/11/2019] - Conference for strategy and tech on big data in London, UK.

MLJobs = Jobs & Careers

We showcase Machine Learning Engineering jobs (primarily in London for now) to help our community stay up to date with great opportunities that come up.

Leadership Opportunities

• Algorithmia is hiring for a VP of Engineering in Seatle, USA
• Fractal Labs is hiring for a VP of Engineering in London

Mid-level Opportunities

• Seldon is hiring for a Senior Machine Learning Engineer in London
• Proportunity is hiring for a Senior Machine Learning Engineer in London
• Atlas ML is hiring for a Lead NLP Engineer in London
• StreetBees is hiring for a Senior Data Scientist in London
• Tractable is hiring for a Senior Deep Learning Engineer

Junior Opportunities

• Migacore is hiring for a Machine Learning Engineer in London
• Babylon Health is hiring for a Machine Learning Engineer in London