Скачать или смотреть Machine Learning Design Patterns | Michael Munn, Google

Design patterns capture best practices and solutions to recurring problems. The recently released O’Reilly book “Machine Learning Design Patterns” covers thirty design patterns that frequently crop up through the various stages of the machine learning process. In this talk, we will discuss in detail three of these tried-and-proven methods: Useful Overfitting, Rebalancing, and Explainable Predictions.

Rebalancing: Many real-world datasets are not perfectly balanced, and it’s important to address this throughout the ML process. The Rebalancing pattern provides various approaches for handling datasets that are inherently imbalanced.

Useful Overfitting: In the Useful Overfitting design pattern we forgo the use of generalization mechanisms, such as dropout, early stopping or use of validation set, because we want to intentionally overfit on the training dataset.

Explainable Predictions: The Explainable Predictions design pattern increases user trust in ML systems by providing users with an understanding of how and why models make certain predictions.

Bio:

Michael Munn

Mike is an ML solutions engineer in Google Cloud. He helps customers design, implement, and deploy machine learning models and teaches the ML Immersion Program in Google’s Advanced Solutions Lab

Topics: machine learning engineering, design patterns, MLOps.

Event details:

This event will be held in English and will be streamed live via our Youtube channel (   / datasciencemilan  . The live streaming will be listed before the event starts.

During the event you will be able to interact and ask questions via the #general channel in our slack workspace. You can request an invite via our website, at the get in touch section, or by following this direct link: https://app.slack.com/client/T1K880GR....

Agenda:

18:30 Data Science Milan community opening

18:40 Talk (50 minutes)

---

Would you be happy to host one of our events? Increase your popularity and be known from our community by hosting one of our interesting events. Contact us at [masked].

If you are interested in doing a lightning talk or want to propose an event, hackathon, panel discussion, roundtable, or any sort of initiative please submit your proposal at Call for speakers or get in touch with one of the members of the staff.

---

This event is supported by IAML (Italian Association of Machine Learning).