Briefly explain what determines whether merging training data sources is risky.
Question: In one to three sentences, explain what factor determines whether merging training data sources, such as user-uploaded and internet images, is risky according to the source.
Sample answer: The riskiness of merging training data sources depends on the flexibility of the learning algorithm. Earlier, less flexible algorithms, like hand-designed features with a linear classifier, faced a real risk of worse performance, while modern flexible algorithms, like large neural networks, face greatly diminished risk.
Key points:
- Algorithm flexibility determines the level of risk
- Earlier algorithms had a real risk of worsening performance
- Modern flexible algorithms have greatly diminished risk
Rubric: Full credit names algorithm flexibility as the determining factor and references both the earlier and modern algorithm examples.
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
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.