Learn Before
How large does a training dev set need to be?
Question: Answer in one to three sentences: What determines an adequate training dev set size?
Sample answer: It only needs to be large enough to evaluate and track the learning algorithm's progress. It is therefore usually smaller than the actual training set.
Key points:
- Large enough for evaluation
- Large enough to track learning progress
- Usually smaller than the actual training set
Rubric: The answer should tie size to evaluation and progress tracking and may note that the set is usually smaller than the training 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
Four Dataset Evaluation for Different Training and Dev/Test Distributions
Training Dev Set Size Guidelines
What distinguishes a training dev set from the actual training set?
Is the training dev set drawn from the training set's distribution?
The algorithm does not _____ on the training dev set.
Match each dataset feature to its role in a training-dev split.
Order the steps for creating and using a training dev set.
Explain why a training dev set is held out despite sharing the training distribution.
Diagnose the flaw in a team's proposed training-dev split.
How large does a training dev set need to be?
Which proposed split correctly creates a training dev set?
Must a training dev set be the same size as the actual training set?