Risk of Merging Training Data Sources Depends on Algorithm Flexibility
Merging user-uploaded images with internet images had a real risk of worsening performance for earlier learning algorithms, such as hand-designed computer-vision features followed by a simple linear classifier. With powerful, flexible algorithms such as large neural networks, that risk has greatly diminished.
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
Adding More Training Data Does Not Always Help
Special Challenges from Different Training and Dev/Test Distributions
Risk of Merging Training Data Sources Depends on Algorithm Flexibility
Shared Label Mapping Across Data Sources
Training and Dev/Test Sets from Different Distributions
Inconsistent Auxiliary Data Source
Approximating Future Dev/Test Data Before Launch
Updating Dev/Test Sets with Actual User Data After Launch
Risk of Starting with Website Images When Future-Like Data Is Unavailable
Development Investment for Dev and Test Sets Requires Judgment
According to Machine Learning Yearning, what is the primary criterion for choosing dev and test sets?
True or False: When building a dev/test set, it is safe to assume the training distribution is the same as the test distribution.
Dev and test sets should contain examples that reflect what you ultimately want to perform well on, rather than only the _____ you happen to have for training.
Why is using a simple 30% random split of available data as your test set problematic when future data differs from training data?
According to ML Yearning, it is generally safe to assume your training data distribution is the same as your test data distribution.
Dev and test sets should be chosen to reflect data you expect to get in the _____ and want to do well on.
Match each dev/test set concept from ML Yearning to its correct description.
Order the steps for correctly choosing dev and test sets according to ML Yearning's guidance.
According to ML Yearning, what should the examples in your dev and test sets primarily reflect?
According to ML Yearning, dev and test sets must always come from the same distribution as the training data.
ML Yearning warns that the test set should not simply be _____ of the available data when future data differs from the training set.
Match each data scenario to the correct dev/test set strategy decision according to ML Yearning.
Order the reasoning steps for deciding whether a proposed dev/test set is well-chosen, per ML Yearning.
Why Standard Data Splits Fail With Different Future Distributions
Dev and Test Set Design for Mobile Image Applications
The Core Criterion for Dev and Test Set Selection
Learn After
Using Additional Internet Images with a Large Enough Neural Network
Why has the risk of merging user-uploaded and internet images diminished today?
True or False: Merging data sources carried a real risk of worse performance with earlier learning algorithms.
Earlier algorithms used hand-designed computer vision features followed by a simple _____ classifier.
Match each algorithm type or factor to its role in the risk of merging training data sources.
Order the reasoning steps for judging the risk of merging training data sources.
Analyze why algorithm flexibility changes the risk of merging different training data sources.
Decide whether merging data sources is risky for a team's specific algorithm choice.
Briefly explain what determines whether merging training data sources is risky.
Which algorithm type is described as carrying real risk when merging data sources?
True or False: Large neural networks eliminate all risk of merging different training data sources.