Machine Learning Yearning



Download free course Machine Learning Yearning, pdf file on 118 pages by Andrew Ng.
AI is transforming numerous industries. Machine Learning Yearning, a free ebook from Andrew Ng, teaches you how to structure Machine Learning projects.

This book is focused not on teaching you ML algorithms, but on how to make ML algorithms work. After reading Machine Learning Yearning, you will be able to:
- Prioritize the most promising directions for an AI project
- Diagnose errors in a machine learning system
- Build ML in complex settings, such as mismatched training/ test sets
- Set up an ML project to compare to and/or surpass human- level performance
- Know when and how to apply end-to-end learning, transfer learning, and multi-task learning.

Table of contents

  • Why Machine Learning Strategy
  • How to use this book to help your team
  • Prerequisites and Notation
  • Scale drives machine learning progress
  • Your development and test sets
  • Your dev and test sets should come from the same distribution
  • How large do the dev/test sets need to be?
  • Establish a single-number evaluation metric for your team to optimize
  • Optimizing and satisficing metrics
  • Having a dev set and metric speeds up iterations
  • When to change dev/test sets and metrics
  • Takeaways: Setting up development and test sets
  • Build your first system quickly, then iterate
  • Error analysis: Look at dev set examples to evaluate ideas
  • Evaluating multiple ideas in parallel during error analysis
  • Cleaning up mislabeled dev and test set examples
  • If you have a large dev set, split it into two subsets, only one of which you look at
  • How big should the Eyeball and Blackbox dev sets be?
  • Takeaways: Basic error analysis
  • Bias and Variance: The two big sources of error
  • Examples of Bias and Variance
  • Comparing to the optimal error rate
  • Addressing Bias and Variance
  • Bias vs. Variance tradeoff
  • Techniques for reducing avoidable bias
  • Error analysis on the training set
  • Techniques for reducing variance
  • Diagnosing bias and variance: Learning curves
  • Plotting training error
  • Interpreting learning curves: High bias
  • Interpreting learning curves: Other cases
  • Plotting learning curves
  • Why we compare to human-level performance
  • How to define human-level performance
  • Surpassing human-level performance
  • When you should train and test on different distributions
  • How to decide whether to use all your data
  • How to decide whether to include inconsistent data
  • Weighting data
  • Generalizing from the training set to the dev set
  • Identifying Bias, Variance, and Data Mismatch Errors
  • Addressing data mismatch
  • Artificial data synthesis
  • The Optimization Verification test
  • General form of Optimization Verification test
  • Reinforcement learning example
  • The rise of end-to-end learning
  • More end-to-end learning examples
  • Pros and cons of end-to-end learning
  • Choosing pipeline components: Data availability
  • Choosing pipeline components: Task simplicity
  • Directly learning rich outputs
  • Error analysis by parts
  • Attributing error to one part
  • General case of error attribution
  • Error analysis by parts and comparison to human-level performance
  • Spotting a flawed ML pipeline
  • Building a superhero team - Get your teammates to read this
Pages118
Size4.1 MB
File typePDF
Downloads220
Created2022-02-03
LicenseCC BY
Author(s) Andrew Ng
Cover of Machine Learning Yearning

Download

  • A Byte of Python

    This is a free book on programming using the Python language. It serves as a tutorial or guide to the Python language for a beginner audience. If all you know about computers is how to save text files, then this is the book for you. This book is written for the latest Python 3, even though Python ...

  • RubyFu

    This book is a great collection of ideas, tricks, and skills that could be useful for Hack..., download free Ruby tutorial in PDF (281 pages) created by RubyFu ....

  • Learning iOS eBook (PDF)

    Download free IOS tutorial course material and training in PDF file 1131 pages....

  • The Official Raspberry Pi Handbook 2021

    Download free course The Official Raspberry Pi Handbook 2021, pdf file on 204 pages by David Crookes, PJ Evans, Gareth Halfacree, Rosie Hattersley, Nicola King, Simon Monk, Mark Vanstone....

  • Effective AWK Programming, 5th Edition

    When processing text files, the awk language is ideal for handling data extraction, report..., download free AWK Programming tutorial in PDF (572 pages) created by ....

  • From Python to NumPy

    NumPy is one of the most important scientific computing libraries available for Python. This book teaches you how to achieve expert level competency to perform complex operations, with in-depth coverage of advanced concepts....

  • Microsoft Platform and Tools for Mobile App Development

    Understanding and creating a mobile app development strategy is an important process for t..., download free Microsoft Platform and Tools for Mobile App Development tutorial in PDF (150 pages) created by Simon Calvert ....

  • Fundamentals of C# programming

    This tutorial is designated to learn the C# language and think like a programmer ,it's a free PDF document under 1122 pages for all level users....

  • 5 Unsung Tools of DevOps

    Download free course 5 Unsung Tools of DevOps, pdf file on 21 pages by O'Reilly Media....

  • Algorithms and Data Structures With Applications to Graphics and Geometry

    An introductory coverage of algorithms and data structures with application to graphics and geometry. ...