High-Value Applications May Need Larger Dev Sets
For mature and important applications such as advertising, web search, and product recommendations, teams may be highly motivated to find even a 0.01% improvement because it directly affects company profits. In that case, the dev set could be much larger than 10,000 examples to detect even smaller improvements.
0
1
Tags
Machine Learning
Deep Learning
Machine Learning Strategy
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Learn After
Why might a team building a high-value application need a dev set much larger than 10,000 examples?
Teams working on mature, high-value applications like advertising may actively pursue accuracy gains as small as 0.01%.
For high-value applications, the dev set may need to be much larger than _____ examples to detect very small improvements.
Match each high-value application domain to the reason why tiny accuracy improvements matter there.
Order the steps for deciding whether a standard 10,000-example dev set is sufficient for a high-value application.
According to Ng, why does a 0.01% accuracy improvement matter in domains like advertising or web search?
A dev set of exactly 10,000 examples is always large enough to detect accuracy improvements relevant to high-value applications like web search.
In high-value applications, teams may be motivated to find even a _____ improvement because it directly affects the company's profits.
Match each concept to its correct role in the reasoning for larger dev sets in high-value applications.
Arrange the reasoning steps Ng uses to justify larger dev sets in high-value applications, in the order he presents them.