Graph-Powered Machine Learning

by Alessandro Negro

Graph-Powered Machine Learning introduces you to graph technology concepts, highlighting the role of graphs in machine learning and big data platforms. You’ll get an in-depth look at techniques including data source modeling, algorithm design, link analysis, classification, and clustering. As you master the core concepts, you’ll explore three end-to-end projects that illustrate architectures, best design practices, optimization approaches, and common pitfalls. Author Alessandro Negro’s extensive experience building graph-based machine learning systems shines through in every chapter, as you learn from examples and concrete scenarios based on his own work with real clients!

Genres: Artificial Intelligence

475 pages, Paperback

Published January 1, 2021

Reviews

[Mike Fowler · Rating 1 out of 5]

Frustrating book that is very repetitive and yet tantalising - you constantly feel like you’re on the verge on enlightenment only to be forestalled page after page. Long passages explaining the motivating scenarios seem to be reworded in each chapter. Examples are in Python, scikit-learn and Neo4j.

Caveat: This book is still in draft form and has been made available as part of Manning’s Early Access Program (MEAP). In particular this means that there has been no copy editing or seeming any proof reading.

[Alex Ott · Rating 4 out of 5]

I read prerelease version of the book...

good overview of the application of the graph approach to solving the problems traditionally solved with machine learning - recommendations, etc.

The biggest drawback from my side - sometimes it too wordy - you need to read a lot (sometimes is not completely related to the topic) before getting to the solving of the real problems.

[Pwyllugh · Rating 2 out of 5]

Didn't get to the good stuff and repeated information over and over again.