Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

A Few Useful Things About Machine Learning

Total questions: 12

Worksheet time: 6mins

Name
Class
Date
1.

Which of these is an example of overfitting in real life?

a)

Memorizing every question from last year’s exam

b)

Practicing general problem-solving strategies

c)

Learning to cook with different ingredients

d)

Training for a marathon by running regularly

2.

Which three components are at the core of any machine learning system?

a)

Prediction, Coding, Testing

b)

Representation, Evaluation, Optimization

c)

Features, Models, Data

d)

Algorithms, Math, Statistics

3.

What happens when a model is too complex and learns noise instead of signal?

a)

 Generalization

b)
  • Underfitting

c)

Overfitting

d)

Optimization

4.

Imagine you’re teaching a robot to make coffee. Which feature would be most useful?

a)
  • The color of the coffee mug

b)

The day of the week

c)

The number of beans used

d)

The robot’s favorite TV show

5.

A production line model predicts defects perfectly on last month’s data but misses new defect types this month. What happened?

a)

Overfitting

b)

Good generalization

c)
  • Feature engineering success

d)

Bias reduction

6.

In demand forecasting, which principle helps decide whether to collect more sales data or engineer better features like promotions and seasonality?

a)
  • Bias–Variance tradeoff

b)

Learning curves

c)

Ensemble methods

d)
  • Theoretical guarantees

7.

An ISE builds a model to predict machine breakdowns. What’s the WORST feature they could use?

a)

Horoscope sign of the machine

b)
  • Machine age

c)

Operator shift

d)

Vibration levels

8.

According to Domingos, what usually matters more than choosing the fanciest algorithm?

a)

Ensemble methods

b)

More computer power

c)

Using bigger models

d)

Feature engineering

9.

Which situation shows high variance (overfitting)?

a)

A neural network predicting every tiny fluctuation in weekly demand

b)

 A linear regression missing seasonal cycles

c)

A model achieving steady performance across datasets

d)

A simulation with simplified assumptions

10.

Why are ensembles (like bagging or boosting) often powerful?

a)
  • They use less data

b)

They average out errors

c)
  • They remove the need for features

d)

They are easier to interpret

11.

Industrial & Systems Engineers can use ML for all of these EXCEPT:

a)

Optimizing supply chain scheduling

b)

Predicting patient flow in hospitals

c)

Detecting defects with computer vision

d)

Playing professional basketball

12.

Biggest lesson from Domingos’ article?

a)

Success in ML depends heavily on representation, evaluation, and features

b)

Always choose the most advanced algorithm

c)
  • Theory is always enough to guide practice

d)
  • Data quality doesn’t matter as much