Why can a traditional algorithm's small-data advantage be uncertain?
Question: Answer in one to three sentences: Why does the source say a traditional algorithm may or may not do better in the small data regime?
Sample answer: Its performance depends on how the features are hand-engineered. With very little data, such as about 20 examples, feature design can matter more than whether the model is logistic regression or a neural network.
Key points:
- Performance depends on hand-engineered features.
- Algorithm choice may have a smaller effect with about 20 examples.
Rubric: The response should state that the outcome depends on feature hand-engineering and connect this dependence to the small data regime.
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
With about 20 training examples, which decision is likely to have the larger effect?
Traditional algorithms always outperform neural networks on small datasets.
With about 20 examples, _____ can matter more than algorithm choice.
Match each small-data claim with its meaning.
Order the reasoning for choosing what to prioritize with very little training data.
Explain why algorithm choice may be secondary in a very small data regime.
Diagnose the priority for a team training models on only 20 examples.
Why can a traditional algorithm's small-data advantage be uncertain?
Which conclusion best reflects the source's comparison across dataset sizes?
With 20 examples, feature design may deserve more attention than switching model families.