Machine Learning Concepts Quiz
This quiz focuses on core machine learning concepts rather than definitions: overfitting and underfitting, features and labels, training and test sets, evaluation and regularisation. It complements the Machine Learning Basics quiz.
What this quiz covers
- Features and labels
- Training and testing data
- Overfitting and underfitting
- Evaluation and regularisation
Study tip: Explain overfitting in your own words with an example; if you can, you understand most of this quiz.
Questions, answers and explanations
1. What is Machine Learning?
- A subset of Artificial Intelligence
- A web development framework
- A database management system
- A programming language
Answer: A subset of Artificial Intelligence
Machine Learning is a branch of AI that enables computers to learn from data.
2. Which programming language is most commonly used for Machine Learning?
- Python
- HTML
- CSS
- PHP
Answer: Python
Python is the most popular language for Machine Learning because of its rich libraries.
3. Which library is widely used for Machine Learning in Python?
- Scikit-learn
- Bootstrap
- React
- Flutter
Answer: Scikit-learn
Scikit-learn provides many machine learning algorithms and tools.
4. Which type of learning uses labeled data?
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- Deep Learning
Answer: Supervised Learning
Supervised learning trains models using labeled datasets.
5. Which type of learning works with unlabeled data?
- Unsupervised Learning
- Supervised Learning
- Reinforcement Learning
- Semi-Supervised Learning
Answer: Unsupervised Learning
Unsupervised learning finds patterns in unlabeled data.
6. Which algorithm is commonly used for classification?
- Decision Tree
- Bubble Sort
- Binary Search
- Dijkstra Algorithm
Answer: Decision Tree
Decision Trees are commonly used for classification tasks.
7. Which algorithm is mainly used for clustering?
- K-Means
- Linear Regression
- Logistic Regression
- Random Forest
Answer: K-Means
K-Means groups similar data points into clusters.
8. Which evaluation metric is commonly used for classification?
- Accuracy
- Mean
- Median
- Variance
Answer: Accuracy
Accuracy measures the percentage of correct predictions.
9. What is a dataset?
- A collection of data
- A programming language
- A web server
- A browser
Answer: A collection of data
A dataset is a structured collection of data used for analysis or training.
10. What is the goal of Machine Learning?
- Enable computers to learn from data
- Build websites
- Create databases
- Develop operating systems
Answer: Enable computers to learn from data
Machine Learning enables systems to improve performance using experience and data.
11. What is overfitting in Machine Learning?
- A model performs very well on training data but poorly on new data
- A model cannot learn from data
- A dataset contains no features
- A model has no parameters
Answer: A model performs very well on training data but poorly on new data
Overfitting happens when a model learns the training data too closely and fails to generalize to unseen data.
12. What is underfitting?
- A model is too simple to capture patterns in the data
- A model memorizes all training data
- A model has too many features
- A model always achieves 100% accuracy
Answer: A model is too simple to capture patterns in the data
Underfitting occurs when a model is too simple to learn the important patterns in the dataset.
13. What is a feature in Machine Learning?
- An input variable used by a model
- The final prediction
- A programming language
- A database
Answer: An input variable used by a model
Features are input variables that provide information to a machine learning model.
14. What is a label in supervised learning?
- The target value the model tries to predict
- A programming language
- A database table
- A training algorithm
Answer: The target value the model tries to predict
A label is the known target or output used when training a supervised learning model.
15. Why is a dataset divided into training and testing sets?
- To evaluate how well the model performs on unseen data
- To make the dataset larger
- To remove all features
- To increase the file size
Answer: To evaluate how well the model performs on unseen data
The training set is used to learn patterns, while the testing set evaluates generalization.
16. What is regression used for?
- Predicting continuous numerical values
- Grouping unlabeled data only
- Deleting data
- Creating web pages
Answer: Predicting continuous numerical values
Regression algorithms predict continuous values such as prices, temperatures, or sales.
17. What is classification used for?
- Predicting categories or classes
- Predicting only continuous numbers
- Cleaning databases
- Creating HTML pages
Answer: Predicting categories or classes
Classification assigns data to categories such as spam or not spam.
18. What is a neural network inspired by?
- The human brain
- A computer keyboard
- A database
- A web browser
Answer: The human brain
Artificial neural networks are inspired by the structure and functioning of biological neural networks.
19. What is Deep Learning?
- Machine Learning using multi-layer neural networks
- A database technology
- A web development language
- A type of operating system
Answer: Machine Learning using multi-layer neural networks
Deep Learning uses neural networks with multiple layers to learn complex patterns.
20. Which technique can help reduce overfitting?
- Regularization
- Removing the test set
- Using random labels
- Ignoring validation
Answer: Regularization
Regularization adds constraints to a model to reduce excessive complexity and help prevent overfitting.