Before You Model: planning and scoping

From Machine Learning Engineering in Action by Ben Wilson

Before we get into how successful planning phases for ML projects are undertaken, let’s go through a simulation of the genesis of a typical project at a company that doesn’t have an established or proven process for initiating ML work.

Multitask Learning

From Deep Learning for Natural Language Processing by Stephan Raaijmakers

This article covers multitask learning for NLP.

Machine Learning as a Pipeline

From Deep Learning Patterns and Practices by Andrew Ferlitsch

Like the best software engineering, modern deep learning uses a pipeline architecture based on reusable patterns.

Fine-Tuning a Pre-Trained ResNet-50

From Transfer Learning in Action Dipanjan Sarkar and Raghav Bali

This article delves into tuning up a pre-trained ResNet-50 with one-cycle learning rate.

Image Classification with Transfer Learning

From Transfer Learning in Action Dipanjan Sarkar and Raghav Bali

This article discusses classifying images using transfer learning.

Why the buzz around GNNs?

From Graph Neural Networks in Action by Keita Broadwater

Building and Using Topologies

From PostGIS in Action, Third Edition by Leo S. Hsu and Regina O. Obe

In this article, you’ll learn what a topology is, how to build a topology from scratch, and how to use commonly available geometry data.

Managing Data Sources in Machine Learning

From Graph-Powered Machine Learning by Alessandro Negro

This article discusses managing data in graph-powered machine learning projects.

Getting to Know GPUs

From Parallel and High-Performance Computing by Robert Robey and Yuliana Zamora

This article takes a deep dive into GPUs.

Deploying Machine Learning Models, Part 5: deployment

In this series, we cover model deployment: the process of putting models to use. In particular, we’ll see how to package a model inside a web service, allowing other services to use it. We also show how to deploy the web service to a production-ready environment.

© 2021 Manning — Design Credits