Learn Before
Using a Dev-Error Learning Curve to Estimate the Benefit of More Data
After adding the desired performance level to a learning curve, visually extrapolating the dev-error curve can help guess how much closer adding more data could get to the desired level. In the passage's example, doubling the training-set size looked plausibly sufficient to reach the desired performance.
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
Learn After
What does visually extrapolating the dev-error curve help estimate?
Visual extrapolation gives a guaranteed prediction of performance after adding data.
Add the desired _____ level to the learning curve before extrapolating dev error.
Match each learning-curve element with its role in estimating the value of more data.
Order the reasoning process for estimating whether more data could reach the desired performance.
Explain how a dev-error learning curve can support a decision to collect more data.
A projected dev-error curve reaches the target after doubling the data. What should the team conclude?
Why should the desired performance level be shown on the learning curve?
Which conclusion best reflects the passage's example learning curve?
A dev-error extrapolation may justify saying that a data increase looks plausible, not certain.