What two observations support the conclusion that more data alone will not fix this learning curve?
Question: Answer in one to three sentences using the behavior of training error and dev error.
Sample answer: As more training data is added, training error can only stay the same or get worse. Dev error is usually higher than training error, so if training error already exceeds the desired level, more data alone is not sufficient for dev error to reach it.
Key points:
- Training error stays the same or rises with more data.
- Dev error is usually higher than training error.
- Training error is already above the desired level.
Rubric: Include both observations and connect them to the insufficiency of adding data alone.
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 is adding more data alone insufficient when training error exceeds the desired performance level?
More data alone can bring dev error to the desired level even when training error remains above that level.
As training data increases, training error can only stay the same or _____.
Match each learning-curve element to its role in diagnosing why more data is insufficient.
Order the reasoning used to conclude that more data alone will not reach the desired performance.
Explain how the training- and dev-error curves prove that more data alone is insufficient.
Diagnose whether a team should expect more data alone to reach its desired error level.
What two observations support the conclusion that more data alone will not fix this learning curve?
Which learning-curve pattern most directly rules out more data as a sufficient solution by itself?
If training error stays unchanged as data is added, dev error can still be expected to cross below a lower desired level.