Page 198 - AI Computer 10

2. What type of neural network is primarily used for image recognition?
Ans. Convolution Neural Network (CNN) is primarily used for image recognition.

3. What distinguishes unsupervised learning from supervised learning?
Ans. Unsupervised learning uses unlabelled data, whereas supervised learning uses labelled data.
4. What does reinforcement learning involve?
Ans. Reinforcement learning involves learning through trial and error via feedback from the environment.
5. Define anomaly detection.

Ans. Anomaly detection is the process of identifying rare items or observations that differ significantly from
the majority of the data.

6. In deep learning, what is required for the training of models?
Ans. Large amount of labelled data is required for the training of deep learning models.
7. Define the term ‘Regression’ in the context of machine learning.
Ans. Regression in machine learning is a learning-based technique for predicting continuous outcomes based
on input features.
8. Write any two applications of neural networks.

Ans. Neural networks are widely used in pattern recognition, facial recognition, customer support chatbot,
vegetable price prediction, etc.

9. What is a perceptron?
Ans. A perceptron is the simplest type of artificial neural network and serves as the fundamental building
block for machine learning models.
10. Write a short note on the Association model.
Ans. Association model is a type of unsupervised learning that involves discovering interesting relationships
between variables in large datasets.
E. Short answer type questions.
1. Explain the following terms:
a. Training Dataset b. Testing Dataset

Ans. a. Training Dataset: A training dataset is a subset of data used to train a machine learning model. It
consists of input-output pairs where the model learns to map the input features to the corresponding
output labels.
b. Testing Dataset: A testing dataset is a subset of data used to evaluate the performance and
generalisation ability of a trained machine learning model. It is distinct from the training dataset and
is crucial for understanding how well the model can perform on unseen data.
2. Differentiate between data feature and data labelling in brief.
Ans. Data Feature: A data feature is an individual measurable property or characteristic of a dataset that is
used as an input in a machine learning model. Features can be thought of as the columns in a data table,
each containing specific information.
Data Labelling: Data labelling is the process of adding meaningful tags or labels to various elements
within a dataset, so that machine learning models can learn from it. In general, labels depend on the
context of the problem we are trying to solve.
3. Explain the term AI Modelling in brief.
Ans. AI Modelling refers to the process of creating algorithms and models that allow machines to mimic
human cognition and perform tasks involving understanding, reasoning, and learning from data. This

64
64