When to Use Noise-Reduction Techniques for Learning Curves
Averaging over multiple subsets and constructing balanced subsets are only worth using after plotting learning curves and finding that the curves are too noisy to reveal the underlying trends. With a large training set, such as over 10,000 examples, and a class distribution that is not very skewed, these techniques usually are not needed.
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
When to Use Noise-Reduction Techniques for Learning Curves
When averaging learning curves over multiple random subsets, what is the correct procedure for each randomly selected small training set?
To reduce noise in a learning curve, you should train a single model on multiple randomly chosen training sets of the same small size.
After training a different model on each random subset of the same small size, you compute and plot the _____ training error and dev set error.
Why does averaging learning curves over multiple random subsets help reveal the true learning trend?
The averaging technique described by Andrew Ng uses sampling with replacement to create the multiple small training sets.
Instead of training just one model on a small set, Ng recommends training _____ different models on different randomly chosen subsets of the same size.
Match each term in the averaging technique to its correct description.
Order the steps of the averaging-over-multiple-random-subsets procedure as described in Machine Learning Yearning.
According to Machine Learning Yearning, approximately how many randomly chosen training subsets should you select when using the averaging technique?
In the averaging technique, a single model is trained jointly on all the randomly chosen small training subsets combined into one larger set.
After training each model on a small subset, you compute both the training error and the _____ error for each model before averaging.
Match each challenge to the element of the averaging technique that directly addresses it.
Order the reasoning steps a practitioner should follow when deciding to apply and interpret the averaging technique for noisy learning curves.
How does averaging learning curves over multiple random subsets reduce noise, and what are the specific steps to execute this technique?
Smoothing a Noisy Dev Set Learning Curve at Small Training Sizes
Sampling Method and Metric Plotting for Learning Curve Noise Reduction
Learn After
When should you consider using techniques that reduce noise in learning curves?
Noise-reduction techniques should be applied before inspecting the initial learning curves.
Use noise-reduction techniques only if learning curves are too _____ to reveal underlying trends.
Match each learning-curve condition to its implication for noise-reduction techniques.
Order the decision process for using learning-curve noise-reduction techniques.
Explain why noise-reduction techniques should follow, rather than precede, an initial learning-curve plot.
Decide whether a team should add noise reduction to already readable learning curves.
What observation must justify averaging learning curves over multiple subsets?
Which dataset most strongly suggests that learning-curve noise reduction is unnecessary?
A large, not-very-skewed dataset usually removes the need for these noise-reduction techniques.