Page 197 - AI Computer 10

3. __________ focuses on identifying rare items or events that differ significantly from the majority data.

4. __________ is characterised by using neural networks with multiple layers to process data.
5. In supervised learning, models learn from __________ datasets that contain both input-output pairs.
6. Unsupervised learning algorithms are designed to find patterns or relationships in __________ data.
7. __________ refers to training models to make a sequence of decisions based on feedback.

8. A __________ dataset is used to evaluate the performance and generalisation ability of a trained machine
learning model.
9. __________ recognition is a notable application of deep learning, where systems identify and understand
spoken language.
10. The purpose of data labelling is to provide clear __________ about the data, allowing for proper
categorisation.
Answers

1. Machine Learning 2. Labels 3. Anomaly Detection
4. Deep Learning 5. labelled 6. unlabelled
7. Reinforcement Learning 8. Testing 9. Speech
10. information

C. State ‘T’ for True or ‘F’ for False statements.
1. Machine learning is a component of artificial intelligence that allows systems to learn from historical
data without explicit programming.
2. In deep learning, large amounts of labelled data are often unnecessary for training models
effectively.

3. The main purpose of object classification is to categorise data into discrete values based
on learned features.

4. Anomaly detection is primarily concerned with finding patterns in customer data.
5. Neural networks are used in deep learning to automatically extract features from high-dimensional
data.
6. Reinforcement learning involves training a model using a dataset with clear input-output pairs.

7. Association rule learning is primarily used for identifying relationships between variables in large
datasets.
8. A testing dataset is used to train the model in supervised learning.
9. Digital recognition tasks in AI can include image and text recognition.

10. Algorithms in reinforcement learning learn from experience based on feedback from their
environment.
Answers
1. T 2. F 3. T 4. F 5. T 6. F

7. T 8. F 9. T 10. T
D. Very short answer type questions.
1. What is the main goal of supervised learning?

Ans. The main goal of supervised learning is to make predictions based on labelled datasets.

63
63