Learn Before
Identify Two Inputs for Setting a Target Error Rate
Question: In one to three sentences, name the two kinds of intuition that can help a team choose a target error rate for a learning system.
Sample answer: One source is intuition about the level of performance people need for the product to feel useful and satisfying. The other is intuition, developed from long work on the problem, about how much additional improvement is realistically achievable in the next few months or year.
Key points:
- Product or user-experience needs
- Realistic near-term improvement based on long-term experience
Rubric: Full credit for identifying both sources: product-focused intuition and long-term improvement intuition.
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
What kind of reference is most useful for choosing a target error rate in a user-facing classifier?
True or False: Long experience with a product can help you judge what improvement is realistic over the next few months or year.
A product team may care about the level of _____ the model must achieve to deliver a strong user experience.
Match each situation to the kind of intuition it uses when choosing a target error rate.
Order the steps for setting a target error rate in a hospital triage classifier.
How can product experience guide a target error rate?
Choosing a Quarterly Target from Years of Operational Experience
Identify Two Inputs for Setting a Target Error Rate
What Experience Usually Builds Good Improvement Intuition?
True or False: A reasonable target error rate can only be estimated from experience with a consumer-facing product.