One Predictor Can Work Across Multiple Data Sources
If two data sources obey the same input-to-label relationship, a single model can learn that rule from both sources. For example, a classifier trained on product photos from a warehouse camera and from a handheld tablet can predict the same label from either source without being told which camera produced the image.
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
Some Data Should Be Left Out of Training
When Development and Test Sets Reflect Different Populations
How Model Capacity Changes the Risk of Mixing Data Sources
One Predictor Can Work Across Multiple Data Sources
Choose evaluation data to match the real-world target
Mismatched Auxiliary Data Source
Building Dev and Test Sets Before Real Users Exist
Refreshing Evaluation Sets After a Product Launch
Using Public Web Images When No Better Future-Like Data Exists
Judging How Much to Invest in Dev and Test Sets
What should determine dev and test set selection?
True or False: You can assume the training set and test set always come from the same distribution.
Development and test sets should reflect the conditions you expect after deployment, not only the _____ available in your training pool.
Why can a simple random test split be a poor choice when the data you expect in the future is different from the data you have now?
You can usually assume the data used for training and the data used for testing come from the same distribution.
Design Dev and Test Sets for the Future
Match each concept about development and test sets to its description.
Order the steps for choosing development and test sets when future data differs from training data.
What should dev and test examples be designed to resemble?
A validation and test set must exactly match the training distribution in every project.
How should a test set be chosen when deployment data will differ?
Match each data scenario to the best dev/test set choice.
Order the reasoning steps for deciding whether a dev/test split is appropriate.
Why a Random 30 Percent Split Can Be Misleading When Future Data Will Differ
Dev and Test Splits for a Field-Photo Classifier
How to Choose Dev and Test Data When Future Data Will Differ
Learn After
Compatible Auxiliary Dataset
What does the shared input-to-output mapping assumption require for a model trained on both storefront and handheld-scan images?
A shared label mapping across two image sources only works if the model is told which source produced each image.
A shared label rule can cover _____ input sources.
Match each element of the shared prediction rule to its correct description.
Order the reasoning steps for deciding whether photos from two collection sources can share one label rule.
Why a common input-to-label rule can make two text datasets useful together
Decide Whether Two Image Collections Can Share One Labeling Rule
When can one model label images from two different capture sources consistently?
What property would let one model handle photos from two different collection channels without knowing which channel each photo came from?
True or False: If photos from an online gallery and frames from a phone app follow the same input-to-label rule, one predictor can learn that rule without being told where each image came from.