现在的位置: 首页人工智能, 英文图书, 软件>正文
Machine Learning Design Patterns
图书分类:人工智能, 英文图书, 软件 暂无评论 ⁄ 被围观 41 次阅读+

Book Description:

The design patterns in this book capture best practices and solutions to recurring problems in machine learning. The authors, three Google engineers, catalog proven methods to help data scientists tackle common problems throughout the ML process. These design patterns codify the experience of hundreds of experts into straightforward, approachable advice.

In this book, you will find detailed explanations of 30 patterns for data and problem representation, operationalization, repeatability, reproducibility, flexibility, explainability, and fairness. Each pattern includes a description of the problem, a variety of potential solutions, and recommendations for choosing the best technique for your situation.

You’ll learn how to:

  • Identify and mitigate common challenges when training, evaluating, and deploying ML models
  • Represent data for different ML model types, including embeddings, feature crosses, and more
  • Choose the right model type for specific problems
  • Build a robust training loop that uses checkpoints, distribution strategy, and hyperparameter tuning
  • Deploy scalable ML systems that you can retrain and update to reflect new data
  • Interpret model predictions for stakeholders and ensure models are treating users fairly

 

Title: Machine Learning Design Patterns: Solutions to Common Challenges in Data Preparation, Model Building, and MLOps
Author: Michael Munn, Sara Robinson, Valliappa Lakshmanan
Length: 408 pages
Edition: 1
Language: English
Publisher: O’Reilly Media
Publication Date: 2020-11-03
ISBN-10: 1098115783
ISBN-13: 9781098115784

下载信息:能赚钱的网盘
标签:, ,

你可能喜欢

0 0 vote
Article Rating
Subscribe
提醒
0 评论
Inline Feedbacks
View all comments
0
Would love your thoughts, please comment.x
()
x