Most direct way to lower variance in deep learning
Question: In a modern deep learning setting, what is the most direct way to lower variance without trying to change the model's bias?
Sample answer: Collect more training examples.
Key points:
- More training data usually lowers variance.
- This step does not directly change bias.
Rubric: The answer must identify collecting or adding more training data as the method.
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
Which change is most likely to lower bias in a modern neural network that is underfitting?
Modern deep learning removes the bias-variance tradeoff entirely.
Reducing variance by adding _____
Match each deep learning strategy with its effect on bias or variance
Order the model-improvement steps when a classifier has both high bias and high variance
Why larger data sets and bigger networks change the bias-variance picture
Improve a transaction-risk classifier
Most direct way to lower variance in deep learning
What most weakens the classic bias-variance tradeoff?
True or False: Making a neural network larger always makes variance much worse.