Practice Underfitting (Intuition) in Math
Use these practice problems to test your method after reviewing the concept explanation and worked examples.
Quick Recap
Underfitting occurs when a model is too simple to capture the true pattern in the data, performing poorly on both training data and new data.
An underfit model is like describing a mountain range as 'about 2,000 metres high'. The number is not crazy, but it misses every peak and valley, and repeating it more confidently does not help. You need more detail, such as a contour map. The comparison has a limit built in: too much detail, mapping every pebble, becomes the opposite problem, overfitting.
Showing a random 20 of 50 problems.
Example 1
mediumA residual plot of a linear fit shows a clear curved pattern. Is the model overfit or underfit, and why?
Example 2
mediumA scatter plot shows a clear parabolic relationship. You fit and get . What model would you try next, and why?
Example 3
mediumAs complexity increases from very low, both train and test error fall together at first. What were they suffering from at low complexity?
Example 4
mediumA learning-curve plot shows train and test error very close and both high, flat across sample size. What does this suggest?
Example 5
easyTo fix underfitting, should you make the model more or less complex?
Example 6
easyA model gets on training data and on test data. Underfit or overfit?
Example 7
easyTrain accuracy , test accuracy . Best diagnosis?
Example 8
easyA student uses (the mean) to predict all exam scores. Training . Explain why this represents maximum underfitting.
Example 9
hardA neural network is trained for only 2 epochs. Both train and validation loss remain high. Best next action?
Example 10
challengeAn analyst applies -means with to a dataset that obviously has natural clusters, then concludes 'there are only two types of customers.' Critique this conclusion in terms of underfitting.
Example 11
mediumA linear classifier achieves accuracy on a 2D dataset that is clearly arranged in concentric circles. Underfit or overfit?
Example 12
easyFitting a straight line to data that clearly follows a curve is an example of ___.
Example 13
mediumA decision tree limited to depth 1 (a 'stump') is fit to a complex dataset. Predicted accuracy . Cause?
Example 14
mediumA linear model gives on data that visibly follows a parabola. What does the low plus visible curve suggest?
Example 15
easyPredicting the mean for every input gives training . What kind of fit is this?
Example 16
hardIn a regression task, residuals plotted against show a clear pattern (curve). What does that pattern reveal about the current model?
Example 17
easyTo fix underfitting you should usually make the model ___.
Example 18
challengeTotal error . A model has bias 6, variance 1 (so error 37); adding capacity changes it to bias 2, variance 5. Did total error improve, and was the original underfit?
Example 19
easyA simple model fails to find a pattern. Does that prove no pattern exists?
Example 20
mediumYou apply heavy regularization () to a linear model. Most coefficients shrink to nearly zero. What happens to bias and variance?