Choose between pipeline components based on their training-data availability.
Case context: A team is designing a non-end-to-end pipeline and is comparing two candidate components. It can easily collect data to train Component A, but collecting data to train Component B would be difficult.
Question: Using only the stated component-selection factor, which component should the team favor, and what should it diagnose about Component B?
Sample answer: The team should favor Component A because its training data can be collected easily. It should diagnose Component B as a weaker candidate under this criterion because the data needed to train it is difficult to collect.
Key points:
- Favor Component A under the stated criterion.
- Component A has easily collectable training data.
- Component B is weakened by difficult data collection.
- The decision concerns a non-end-to-end pipeline.
Rubric: The response should favor Component A, identify easy training-data collection as the reason, and characterize Component B only in terms of its weaker training-data availability.
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
Intermediate Module Data Availability Favors Multi-Stage Pipelines
What important factor should guide component selection in a non-end-to-end pipeline?
Training-data availability matters when selecting components for a non-end-to-end pipeline.
Complete the criterion: Choose components for which training data can be collected _____.
Match each pipeline-selection term with its source-grounded meaning.
Order the reasoning process for selecting trainable pipeline components.
Explain why training-data availability belongs in pipeline component selection.
Choose between pipeline components based on their training-data availability.
How should a designer evaluate data availability for a candidate pipeline component?
Which candidate best satisfies the stated training-data criterion?
A component may be selected without considering whether its training data is easy to collect.