Learn Before
Analyzing the utility of learning curves
Question: Explain what a learning curve is and why it might be considered an informative technique in machine learning.
Sample answer: A learning curve is a diagnostic plot that graphs a learning algorithm's dev-set error against the number of training examples used. It is informative because it visually demonstrates how the algorithm's performance on unseen data (the dev set) changes as it is exposed to more training data. This allows practitioners to observe trends and make informed decisions.
Key points:
- Plots dev-set error
- Plots against number of training examples
- Considered highly informative for observing trends
Rubric: The student must define the axes of a learning curve (dev-set error vs. number of training examples) and explain its informational value.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Constructing a Learning Curve by Varying Training Set Size
Dev-Set Error Should Decrease as Training Set Size Increases
Desired Error Rate for a Learning Algorithm
Using a Dev-Error Learning Curve to Estimate the Benefit of More Data
Training Error Plot for Estimating the Effect of More Data
Interpreting Learning Curves with Training and Dev Error
Small Training Sets Can Make Learning Curves Noisy
Identifying the axes of a learning curve
Purpose of a learning curve
A learning curve plots your _____ error against the number of training examples.
Components of a learning curve
Steps to construct a learning curve
Analyzing the utility of learning curves
Applying learning curves to diagnose performance
Defining a learning curve
The dependent variable in a learning curve
Informational value of learning curves