Deciding Whether to Average Learning Curves
Question: Answer in one to three sentences: What should you check before deciding to average learning curves across several subsets?
Sample answer: First inspect the plotted curves to see whether random fluctuations are hiding the overall pattern. If the curves already show a clear trend, then averaging across multiple subsets is not necessary.
Key points:
- Plot the learning curves before changing the evaluation method.
- Use averaging only when the curves are noisy enough that the trend is hard to read.
Rubric: Credit answers that mention both examining the curves first and confirming that noise makes the underlying trend difficult to see.
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
When is it worth considering methods that make learning curves easier to interpret?
It is best to smooth the training and validation curves before looking at them for the first time.
Use noise-reduction methods only when the learning curve is too _____ to show the underlying pattern clearly.
Decide When Noise-Reduction Methods Are Worth Considering
Order the steps for deciding whether to smooth noisy learning curves.
When to Use Noise-Smoothing Methods for Learning Curves
Decide whether additional noise-reducing steps are needed for a learning curve.
Deciding Whether to Average Learning Curves
Which situation least suggests that learning-curve noise reduction is needed?
A very large, fairly balanced training set usually makes these noise-reduction tricks unnecessary.