Learn Before
In one to two sentences, define Recall for a cat classifier.
Question: In one to two sentences, define what Recall means for a cat classifier evaluated on a dev or test set.
Sample answer: Recall is the percentage of all actual cat images in the dev or test set that the classifier correctly labeled as a cat.
Key points:
- Recall is a percentage
- Based on all actual cat images in the dev/test set
- Measures correctly labeled cat images out of that true set
Rubric: Full credit: mentions that Recall is a percentage of all true/actual cat images correctly labeled as cat. Partial credit: vague or incomplete definition. No credit: incorrect or unrelated definition.
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 does the Recall of a cat classifier measure?
True or False: Recall is based on the classifier's predicted labels, not the true cat images.
Recall is the percentage of all cat images in the dev or test set that the classifier correctly labeled as a _____.
Match each term to its correct description related to Recall.
Order the steps to compute Recall for a cat classifier on the dev/test set.
Explain why Recall alone only tells part of the story about a cat classifier's performance.
Diagnose why a cat classifier has low Recall despite seeming to perform well overall.
In one to two sentences, define Recall for a cat classifier.
Which set of images forms the basis for calculating Recall?
True or False: A classifier that misses many true cat images will have a lower Recall.