Learn Before
Tiny Training Samples Make Learning Curves Unstable
When only a few training examples are used, each learning-curve point can vary a lot because the random subset may be unusually easy or unusually hard. A small sample might also overinclude noisy labels, borderline cases, or other awkward examples. This effect is more likely when the classes are highly imbalanced or when the task has many classes, since a tiny draw is then less likely to reflect the full data set.
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 Performance Curve from Different Training Set Sizes
Larger Training Sets Usually Lower Dev-Set Error
Target Error Rate on a Learning Curve
Using a Development-Set Curve to Estimate the Payoff of More Data
Using Training Error to Judge the Value of More Data
Why plot training and development error together on a learning curve?
Tiny Training Samples Make Learning Curves Unstable
What are the axes of a learning curve?
A learning curve shows error versus network depth.
Learning Curves and Validation Error
Parts of a learning curve
Constructing a learning curve for model selection
What a learning curve shows
Using a learning curve to judge whether more data will help
What a Learning Curve Shows
What belongs on the vertical axis of a learning curve?
A learning curve is less informative than a single validation score.
Learn After
Averaging Errors from Several Small Training Samples
Balanced Small Samples Help Learning Curves Stay Stable on Imbalanced or Multi-Class Data
Why can a learning-curve value jump around when it is measured on a tiny random training sample?
A tiny random training sample can make the measured learning-curve error swing noticeably up or down.
A tiny sample with many unclear or incorrect labels is unusually _____.
Match each small-sample condition to its effect on a learning-curve estimate.
Put the checks in a sensible order for explaining a strange value on a tiny sample.
Why can a training curve wobble when the sample size is very small?
Explain a spike caused by a tiny imbalanced sample.
Why can learning-curve values be especially erratic for very small training samples?
Which situation makes a tiny random sample least likely to represent the full dataset?
A very small random sample is less likely to be misleading when the number of classes is large.