Learn Before
Starting error analysis without predefined categories.
Question: According to Machine Learning Yearning, should you be concerned if you begin your error analysis without any predefined error categories in mind? Briefly explain the recommended initial step to generate categories.
Sample answer: No, you should not worry if you start with no categories. The recommended first step is to simply look at a couple of misclassified images, which will typically inspire a few ideas for initial error categories.
Key points:
- Do not worry about lacking initial categories.
- Look at a few images to generate category ideas.
Rubric: 1 point for stating not to worry about starting without categories; 1 point for explaining that looking at a few initial images will generate ideas for categories.
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
Which of the following best describes the nature of error analysis in machine learning, according to Machine Learning Yearning?
True or False: According to Machine Learning Yearning, you must define all error categories before you begin reviewing misclassified examples.
In Machine Learning Yearning, Ng states that after looking at a couple of misclassified images, you might come up with a few ideas for error _____.
Match each phase of the iterative error analysis process to its correct description.
Place the steps of one iterative error analysis cycle in the correct order as described in Machine Learning Yearning.
During error analysis you discover a new error category after completing your first manual categorization pass. What should you do next?
True or False: In Machine Learning Yearning, Ng indicates that discovering new error categories during analysis may require revisiting previously examined examples.
After thinking of new categories during error analysis, you should re-examine examples in light of the _____ categories.
Match each characteristic of the error analysis process to the label that best describes it, as presented in Machine Learning Yearning.
Order the reasoning steps that explain why error analysis benefits from being iterative rather than a single pass.
Explain the iterative nature of error analysis.
Managing new categories during a computer vision error analysis.
Starting error analysis without predefined categories.