In one to three sentences, why do shared similarities between image sources make additional training data useful?
Question: Briefly explain, in one to three sentences, why shared similarities between internet images and mobile-app images make additional internet images useful for training.
Sample answer: Because internet images and mobile-app images share some similarities in appearance, the neural network can apply knowledge it learns from internet images to mobile-app images, making the additional internet data useful despite coming from a different source.
Key points:
- Shared similarities between internet and mobile-app images
- Knowledge acquired from internet images can transfer to mobile-app images
Rubric: Full credit for mentioning shared similarities and knowledge transfer between the two image sources; partial credit for only mentioning more examples without explaining transfer.
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
Why can a neural network apply knowledge from internet cat images to mobile-app images?
True or False: Additional internet images give the network more examples of what cats do or do not look like.
Internet images and user-uploaded mobile app images share some _____.
Match each image source to its role in helping the neural network recognize cats.
Order the reasoning steps explaining why additional internet images help mobile-app cat classification.
Explain why shared similarities between two image sources make additional training data useful.
Diagnose why adding internet cat images could help a mobile app's cat classifier.
In one to three sentences, why do shared similarities between image sources make additional training data useful?
What effect does adding 20,000 additional internet images have on the neural network, per the source?
True or False: A neural network can apply knowledge acquired from internet images to mobile app images.