Subscribe to the Machine Learning Engineer Newsletter

Receive curated articles, tutorials and blog posts from experienced Machine Learning professionals.

Issue #66
We are proud to announce we have reached over 2500 subscribers for the ML Engineer Newsletter 🚀 and the open source Production Machine Learning repo has reached 3000 stars 🔥🔥🔥 a massive thank you to all our subscribers and community members for all your support ✨👏🎉😃 #LetsKeepDoingThis
This week in Issue #66:
Forward  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! We have received a lot of great suggestions in the past, thank you very much for everyone's support!
Machine Learning Mastery has put together a great resource providing a step by step guide on how to train a PyTorch machine learning model. The article covers every step including installation, ML lifecycle (data prep, training, evaluation), and even going further into developing a MLP for multiclass & regression and a CNN for image classification.
A fantastic resource that has put together a very comprehensive list of resources related to MLOps, or the topic surounding the components required to productionise machine learning. This resource contains multiple different themes including references, papers, talks, existing ML systems, and more.
The Data Exchange Podcast comes back this week in conversation with Hypercube Founder Edo Liberty, focusing primarily on how deep learning can be used in search & information retrieval. This podcast includes Edo's experience, deep learning & IR, challenges when building information retrieval tools at scale, and deep learning based search including enterprise e2e deep search paltforms
SHAP (SHapley Additive exPlanations) is an algorithm which provides model-agnostic (black box), human interpretable explanations suitable for regression and classification models applied to tabular data. This method is a member of the additive feature attribution methods class; feature attribution refers to the fact that the change of an outcome to be explained (e.g., a class probability in a classification problem) with respect to a baseline (e.g., average prediction probability for that class in the training set) can be attributed in different proportions to the model input features. The Alibi Explain OSS project has implemented this technique and has put together several jupyter notebook examples to implement this algorithm across various models.
One of the biggest challenges operations groups will face over the coming year will be learning how to support AI- and ML-based applications. The OReilly team has put together a comprehensive high level overview of the probelm of managing machine learning at scale. In this article Mike Loukides provides a high level overview of this challenge, together with some of the components that may comprise the solutions, as well as examples.
The topic for this week's featured production machine learning libraries is Industrial Strength NLP. 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:
  • 🤗 Transformers - Huggingface's library of state-of-the-art pretrained models for Natural Language Processing (NLP).
  • Grover - Grover is a model for Neural Fake News -- both generation and detection. However, it probably can also be used for other generation tasks.
  • Kashgari - Kashgari is a simple and powerful NLP Transfer learning framework, build a state-of-art model in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS), and text classification tasks.
  • Github's Semantic - Github's text library for parsing, analyzing, and comparing source code across many languages .
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
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:
  • 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