Page 202 - AI Computer 10

the user tags as spam and adds them into the training dataset for the next iteration of training. Thus, it
learns with experience and usage over a period.
5. What is an Artificial Neural Network? Explain the layers in an artificial neural network.

Ans. A neural network is built to mimic the functionality of a human brain. The human brain is a neural
network made up of multiple neurons. Similarly, an Artificial Neural Network (ANN) is made up of
multiple perceptrons. A neural network consists of three important layers:
● Input Layer: As the name suggests, this layer accepts all the inputs provided by the programmer.
● Hidden Layer: This layer is located between the input and the output layer. In this layer, computations
are performed which result in the output. There can be any number of hidden layers.
● Output Layer: The inputs go through a series of transformations via the hidden layer which finally
results in the output that is delivered via this layer.
6. Differentiate between classification and regression algorithms with the help of suitable examples.

Ans. Classification algorithms help in dividing the dataset into classes based on different parameters. In
Classification, a computer program is trained on the training dataset and based on that training it
categorises the data into different classes. The task of the classification algorithm is to find the mapping
function to map the input (x) to the discrete output (y).

Example: A good example of classification algorithm is email spam detection. The model is trained on the
basis of millions of emails on different parameters, and whenever it receives a new email, it identifies
whether the email is spam or not.

Regression is a process of finding the correlations between dependent and independent variables. It
helps in predicting the continuous variables such as prediction of market trends, prediction of house
prices, etc. The task of the regression algorithm is to find the mapping function to map the input variable
(x) to the continuous output variable (y).

Example: A goodness of a Regression model is weather forecasting. In weather prediction, the model is
trained on the past data, and once the training is completed, it can easily predict the weather for future
days, based on a number of climate factors such as pressure, temperature, wind speed, humidity, etc.
G. Competency-based questions.
1. A company wants to segment its customers based on purchasing behaviour without any predefined
categories. Which type of machine learning technique should be applied?
a. Supervised learning b. Unsupervised learning

c. Rule-based learning d. Reinforcement learning
2. A healthcare company wants to detect diseases from X-ray images. Which type of machine learning
model be more effective for this purpose?
a. Regression learning b. Associati on rules

c. Clustering d. Convoluti onal neural network
3. You are developing an AI agent for a self-driving car. The system must learn to navigate roads efficiently
and avoid obstacles. Which machine learning technique is most suitable?
a. Regression learning b. Supervised learning

c. Reinforcement learning d. Convoluti onal neural network
Answers
1. (b) 2. (d) 3. (c)

68
68