Machine Learning Yearning
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
| Pages | 118 |
|---|---|
| Size | 4.1 MB |
| File type | |
| Downloads | 220 |
| Created | 2022-02-03 |
| License | CC BY |
| Author(s) | Andrew Ng |
Others machine learning tutorials
Others related eBooks about Machine Learning Yearning
-
.NET Microservices
This guide is an introduction to developing microservices-based applications and managing ..., download free .NET tutorial in PDF (350 pages) created by Mike Rousos ....
-
Think Perl 6: How to Think Like a Computer Scientist
Want to learn how to program and think like a computer scientist? This practical guide gets you started on your programming journey with the help of Perl 6, the younger sister of the popular Perl programming language. Ideal for beginners, this hands-on book includes over 100 exercises with multiple ...
-
Vue.js Succinctly
Download free course Vue.js Succinctly, pdf file on 101 pages by Ed Freitas....
-
Learning Ruby on Rails
Download free course Learning Ruby on Rails, pdf file on 291 pages by Stack Overflow Community....
-
Python Data Science Handbook
Download free course Python Data Science Handbook, pdf file on 548 pages by Jake VanderPlas....
-
Financial Numerical Recipes in C++
Download free course Financial Numerical Recipes in C++, pdf file on 264 pages by Bernt Arne Ødegaard....
-
Optimizing software in C++
This is an optimization manual for advanced C++ programmers. This book are not for beginne..., download free C++ tutorial in PDF (176 pages) created by Agner Fog ....
-
Modern Perl
Modern Perl is one way to describe how experienced and effective Perl 5 programmers work. They use language idioms. They take advantage of the CPAN. They're recognizably Perlish, and they show good taste and craftsmanship and a full understanding of Perl. ...
-
Raspberry Pi Projects Book
Download free course Raspberry Pi Projects Book, pdf file on 204 pages by Wes Archer, David Crookes, PJ Evans, Gareth Halfacree, Rosie Hattersley, Nicola King, Ben Nuttall, Marc Scott, Danny Staple, Mark Vanstone....
-
Getting started with Hibernate
Download free Hibernate tutorial course in PDF, training file in 14 chapters and 39 pages. Free unaffiliated ebook created from Stack OverFlow contributor....