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
Pages : 118
Size : 4.1 MB
File type : PDF
Downloads: 131
Created: 2022-02-03
License: CC BY
Author(s): Andrew Ng
Machine Learning Yearning

Warning: Trying to access array offset on false in /home/tutovnfz/public_html/article.php on line 233

Others machine learning Tutorials

Understanding Machine Learning

Reinforcement Learning: An Introduction, Second Edition

Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers

Overview of Machine Learning

A Brief Introduction to Machine Learning for Engineers

Others related eBooks about Machine Learning Yearning

Programming in Lua

This book is for students and professionals who are intrigued by the prospect of learning and using a powerful language that provides a rich infrastructure for creating programs. No programming knowledge is necessary to benefit from this book except for the section on Lua bindings, which requires so...

Elementary Algorithms

Download free course Elementary Algorithms, pdf file on 642 pages by Larry LIU Xinyu....

Python and the XML

Parser of HTML and XML with python and library Python Programming Course Tutorial Computing Learning....

C++ Exercices with solutions

Download free document in PDF about C++ language, exercices and solutions for beginners and intermediate level students....

Algorithmic Problem Solving with Python

This book uses Python to introduce folks to programming and algorithmic thinking. It is sharply focused on classical algorithms, but it also gives a solid understanding of fundamental algorithmic problem-solving techniques. ...

Android Application Development for the Intel Platform

Download free course Android Application Development for the Intel Platform, pdf file on 508 pages by by Ryan Cohen, Tao Wang....

Building iPhone Apps with HTML, CSS, and JavaScript

Download free course Building iPhone Apps with HTML, CSS, and JavaScript, pdf file on 186 pages by by Jonathan Stark....

Is Parallel Programming Hard, And, If So, What Can You Do About It?

Download free course Is Parallel Programming Hard, And, If So, What Can You Do About It?, pdf file on 601 pages by Paul E. McKenney....

An Introduction to Machine Learning

Download free course An Introduction to Machine Learning, pdf file on 348 pages by by Miroslav Kubat....

IPython Interactive Computing and Visualization Cookbook

This book contains many ready-to-use, focused recipes for high-performance scientific computing and data analysis, from the latest IPython/Jupyter features to the most advanced tricks, to help you write better and faster code. You will apply these state-of-the-art methods to various real-world examp...