Case Study

Determine how to visualize target performance for a speech project's learning curve.

Case context: You are building a speech recognition system. To track progress, you have plotted the dev-set error on a learning curve. You also have a specific level of error that you hope your learning algorithm will eventually achieve.

Question: According to the principles of desired error rate analysis, what should you do with this desired level of performance to help evaluate your system?

Sample answer: You should add the desired level of performance directly to your learning curve. This provides a visual target on the curve to compare against your dev-set error.

Key points:

  • A desired error rate is a level of error one hopes the learning algorithm will eventually achieve.
  • The desired level of performance should be added to the learning curve.

Rubric: The answer must state that the developer should add the desired level of performance to the learning curve.

0

1

Updated 2026-05-27

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI