Machine Learning Basics

1. What is Machine Learning?

 a) A type of programming language

 b) A field of study that gives computers the ability to learn without being explicitly
programmed

 c) A hardware component

 d) A type of database

 Answer: b) A field of study that gives computers the ability to learn without being
explicitly programmed

2. Which of the following is a key application of Machine Learning?

 a) Image and speech recognition

 b) Data entry

 c) Web development

 d) Network security

 Answer: a) Image and speech recognition

Definitions

3. Who defined Machine Learning as "the study that gives computers the ability to learn without
being explicitly programmed"?

 a) Tom Mitchell

 b) Arthur Samuel

 c) Jason Brownlee

 d) Dictionary.com

 Answer: b) Arthur Samuel

4. According to Tom Mitchell, a program can be said to learn from experience E with respect to
some class of tasks T and performance measure P if:

 a) Its performance at tasks in T, as measured by P, improves with experience E

 b) It can solve any problem

 d) It can store more data

 Answer: a) Its performance at tasks in T, as measured by P, improves with experience

Applications

5. Which of the following is NOT an application of Machine Learning?

 a) Face Recognition

 b) Handwriting Recognition

 c) Autonomous cars

 d) Manual data entry

 Answer: d) Manual data entry

6. Machine Learning is important because:

 a) It can handle and process enormous amounts of data

 b) It can adapt to changes over time

 c) It enables automation of repetitive tasks

 d) All of the above

 Answer: d) All of the above

Classification of Machine Learning

7. Which of the following is NOT a type of Machine Learning?

 a) Supervised learning

 b) Unsupervised learning

 c) Semi-supervised learning

 d) Manual learning

 Answer: d) Manual learning

8. In supervised learning, the given data is:

 a) Unlabeled
  b) Labeled

 c) Random

 d) Irrelevant

 Answer: b) Labeled

Supervised Learning

9. Which of the following is an example of a supervised learning problem?

 a) Predicting house prices

 b) Customer segmentation

 c) Dimensionality reduction

 d) Game-playing AI

 Answer: a) Predicting house prices

10. Which algorithm is used in supervised learning?

 a) K-Means Clustering

 b) Principal Component Analysis (PCA)

 c) Linear Regression

 d) Autoencoders

 Answer: c) Linear Regression

Unsupervised Learning

11. In unsupervised learning, the data is:

 a) Labeled

 b) Unlabeled

 c) Structured

 d) Preprocessed

 Answer: b) Unlabeled

12. Which of the following is an example of an unsupervised learning algorithm?

 b) Neural Networks

 c) K-Means Clustering

 d) Support Vector Machines

 Answer: c) K-Means Clustering

Reinforcement Learning

13. In reinforcement learning, an agent learns to make decisions by:

 a) Following a set of rules

 b) Interacting with its environment

 c) Analyzing historical data

 d) Using labeled data

 Answer: b) Interacting with its environment

14. Which of the following is an example of reinforcement learning?

 a) Predicting house prices

 b) Customer segmentation

 c) Game-playing AI

 d) Dimensionality reduction

 Answer: c) Game-playing AI

Semi-Supervised Learning

15. Semi-supervised learning leverages:

 a) Only labeled data

 b) Only unlabeled data

 c) Both labeled and unlabeled data

 d) Neither labeled nor unlabeled data

 Answer: c) Both labeled and unlabeled data

16. A dataset usually consists of:

 a) Features and labels

 b) Algorithms and models

 c) Training and testing data

 d) Loss functions

 Answer: a) Features and labels

17. The process of feeding data to an ML algorithm to help it learn patterns is called:

 a) Testing

 b) Validation

 c) Training

 d) Deployment

 Answer: c) Training

18. The loss function measures:

 a) The difference between the model’s predictions and the actual outcomes

 b) The amount of data processed

 c) The speed of the algorithm

 d) The complexity of the model

 Answer: a) The difference between the model’s predictions and the actual outcomes

Overfitting & Underfitting

19. Overfitting occurs when:

 a) A model learns the training data too well, including noise and outliers

 b) A model is too simple to capture the underlying patterns in the data

 c) The data is insufficient

 d) The algorithm is too complex

20. Underfitting occurs when:

 a) A model learns the training data too well

 b) A model is too simple to capture the underlying patterns in the data

 c) The data is too complex

 d) The algorithm is too simple

 Answer: b) A model is too simple to capture the underlying patterns in the data

Machine Learning Process

21. The first step in the machine learning process is:

 a) Model Training

 b) Data Collection

 c) Model Evaluation

 d) Deployment

 Answer: b) Data Collection

22. Which step involves cleaning and formatting data, handling missing values, and performing
feature scaling or encoding?

 a) Data Collection

 b) Data Preprocessing

 c) Model Selection

 d) Model Training

 Answer: b) Data Preprocessing

23. Model Evaluation involves:

 a) Gathering relevant data

 b) Cleaning and formatting data

 c) Evaluating the model’s performance using test data and metrics like accuracy,
precision, recall
  d) Deploying the trained model into a production environment

 Answer: c) Evaluating the model’s performance using test data and metrics like
accuracy, precision, recall

24. Model Tuning is the process of:

 a) Gathering relevant data

 b) Cleaning and formatting data

 c) Optimizing hyperparameters and improving model performance

 d) Deploying the trained model into a production environment

 Answer: c) Optimizing hyperparameters and improving model performance

Summary and Conclusion

25. Machine Learning is a branch of:

 a) Data Science

 b) Artificial Intelligence

 c) Software Engineering

 d) Computer Networking

 Answer: b) Artificial Intelligence

26. The three main types of machine learning are:

 a) Supervised, Unsupervised, and Reinforcement Learning

 b) Supervised, Unsupervised, and Semi-supervised Learning

 c) Supervised, Semi-supervised, and Reinforcement Learning

 d) Unsupervised, Semi-supervised, and Reinforcement Learning

 Answer: a) Supervised, Unsupervised, and Reinforcement Learning

27. Which of the following is NOT a step in the machine learning process?

 a) Data Collection

 b) Data Preprocessing

 c) Model Training
  d) Data Entry

 Answer: d) Data Entry

28. Machine Learning has numerous applications across industries, making it one of the most:

 a) Expensive technologies today

 b) Transformative technologies today

 c) Complex technologies today

 d) Traditional technologies today

 Answer: b) Transformative technologies today

29. Which of the following is an example of a machine learning application in communication?

 a) Spam filtering (e-mail)

 b) Predicting house prices

 c) Customer segmentation

 d) Game-playing AI

 Answer: a) Spam filtering (e-mail)