Best of ML Engineered in 2020 (Most Popular Episodes and Most Clicked Links)
For the last newsletter of 2020, I wanted to highlight the “best of” content I produced and featured since starting ML Engineered. Below you’ll find the top 5 most-downloaded podcast episodes and most-clicked newsletter links.
But before we get to that, a follow-up from last week:
More on Auto-Encoders for Out of Distribution Detection
In last week’s newsletter, I linked to Alejandro Saucedo’s excellent article on production ML monitoring, noting his use of auto-encoders for out of distribution detection for complex data.
Since then I’ve done additional reading on the topic, learning, among other things, that it can be viewed as a particular type of anomaly detection, of which there is substantial literature for. I’m not quite sure how production-ready this type of research is, and would love to explore it’s possible use at work this year if I get the chance.
Regardless, here are the papers I found most useful on the topic:
- (Chalapathy & Chawla, 2019) Deep Learning for Anomaly Detection: A Survey
- (Ren et al., 2019) Likelihood Ratios for Out-of-Distribution Detection
- (Pang et al., 2020) Deep Learning for Anomaly Detection: A Review
- (Bulusu et al., 2020) Out-of-Distribution Detection in Deep Learning: A Survey
5 Most Popular ML Engineered Episodes
- Yannic Kilcher: Explaining Papers on Youtube, Why Peer Review is Broken, and the Future of the Field
- Shreya Shankar: Lessons learned after a year of putting ML into production
- Josh Tobin: Research at OpenAI, Full Stack Deep Learning, ML in Production
- Luigi Patruno: ML in Production, Adding Business Value with Data Science, “Code 2.0”
- Why Multi-Modality is the Future of Machine Learning w/ Letitia Parcalabescu (University of Heidelberg, AI Coffee Break)
5 Most Clicked Newsletter Links
- “High Performance Natural Language Processing” An ACL 2020 tutorial containing an overview of all the recent advances in deep learning for NLP
- “Challenges in Deploying Machine Learning” An awesome survey of case studies by University of Cambridge researchers on production ML
- “Louis Dorard’s Machine Learning Canvas” A super useful tool to get each team involved in an ML project on the same page (literally)
- “Made With ML’s Applied ML” Goku Mohandas’s pivot to online courses teaching practical machine learning
- “Underspecification Presents Challenges for Credibility in Modern Machine Learning” A new Google ML engineering paper highlighting an incredibly pernicious issue
Machine Learning Engineered
I mentioned last week that I had to skip an episode release because of guest reschedulings. Since then, I’ve recorded five episodes, which was fun but extremely tiring. Rest assured, I won’t be missing another release! Also, in case you missed it, I wrote up a study guide for aspiring ML engineers that lays out a clear starting path and contains a list of resources that I and my friends have learned from. Read the Study Guide In this week's edition: My Interview on the MLOps Community podcast...
There’s no podcast episode this week due to an unfortunate coincidence of multiple guests needing to reschedule. My apologies, I’ll be doing my best in the future to not let this happen again. That doesn’t mean I don’t have any new content for this week, though! Today I’m releasing an article that answers one of the most common questions I get: “I want to learn machine learning, where do I start / what do I do?” When I was first getting started in ML, it was pretty straightforward: there was...
After a month off from releasing original interviews on the podcast feed, I’m so excited to be sharing this episode with all of you! Aether Biomachines is one of the most interesting machine learning startups I’ve ever come across and I was thrilled to interview the founder, Pavle Jeremic. Building a Post-Scarcity Future using Machine Learning “How can we make sure that the economy is so productive that the desperation that leads people to commit atrocities never happens?” In this episode,...