Chapter 3

Neural Network
1. _____ is an instance of deep learning technology.
Ans. Neural Network
2. Neural Network is an instance of _________ technology.
Ans. Deep Learning
3. What are the two main reasons driving the popularity of Deep Learning?
Ans. Data-Required huge amount of labelled
Complex Applications-Solved complicated applications with increasing accuracy.
4. ______ systems/approach are continuously updated.
Ans. Learning-based

5. ________ systems/approach are static in nature.

Ans. Rule-based

6. Machine learning algorithms are often categorized into three types. Write their names.
Ans. Supervised Learning, Unsupervised Learning, Reinforcement Learning

7. Classification is a type of ________ learning.

Ans. Supervised

8. Regression is a type of _______ learning.

Ans. Supervised

9. Clustering is a type of ______ learning.

Ans. Unsupervised

10. ______ model classifies the given dataset(input) on the basis of related class labels.
Ans Classification

11. ______ model classifies datasets according to the rules given to it.
Ans. Classification

12. ______ model works on labelled and discrete datasets.

Ans. Classification

13. _____ model works on continuous data.

Ans. Regression

14. ______ model predicts the output based on patterns and relationships within the input
data.
Ans. Regression

15. ______models are used to identify similarities and differences among discrete datasets.
Ans. Clustering
16. Which AI model works on continuous data?
Ans. Regression

17. In which models, the dataset fed to machine is labelled?

Ans. Classification

18. Which is the only type of data regression works with?

Ans. Continuous

19. Classification and Clustering works on _________ datasets.

Ans. Discrete

20. Regression is an example of _________ learning.

Ans. Supervised Learning

21. Identify the algorithms based on the given graph and explain.

(a) (b)

(c)

Ans. a. Regression b. Clustering c. Classification

22. Give an example of Classification model.
Ans. Email spam detection
23. The first Artificial Neural Network (ANN), called ______ was invented in 1958 by
psychologist Frank Rosenblatt.
Ans. Perceptron
24. How many layers does an Artificial Neural Network (ANN) consist of?
Ans. Three- Input, Hidden and Output
25. In which layer of an ANN, does processing take place?
Ans Hidden Layer
26. ______ requires huge amount of labelled data.
Ans. Deep Learning
27. The large neural network produces better results with _______ amount of input data.
Ans. large
28. ANN is made up of artificial ________.
Ans. Neurons
29. ANNs are made up of _______ nodes which imitate biological neurons of the human
brain.
Ans. Multiple
30. In general, a neural network consists of an input layer, an output layer and one or more
______ layers.
Ans Hidden Layer
31. ______ are the core processing unit of ANN.
Ans. Neurons
32. ANN is made up of three basic layers- input, ______ and hidden.
Ans. Output
33. The number of hidden layers and nodes varies based on the ____________.
Ans. Complexity of the task.
34. A neuron is made up of a cell body(soma), synapses, axon and ________.
Ans. Dendrites
35. _______ are the building blocks of human nervous system.
Ans. Neurons
36. What is the full form of ANN?
Ans. A- Artificial
N- Neural
N- Network
37. Each node of hidden layer has its own _________ algorithm.
Ans Machine learning
38. A neuron in the human brain is composed of four parts. Name them.
Ans. Soma (cell body), synapses, axon and dendrites
39. Which of the following statement is incorrect?
a) Neural network is based on the basis of machine’s capability and working
b) neural network is used for large datasets.
c) Neural network technique based on three layers.
d) Every neural network every node is essentially a machine learning algorithm.
Ans. a)

40. Neural network systems are modelled on the _______ and nervous system.
Ans Human Brain
41. Write the names of two types neural networks.
Ans 1. Artificial Neural Network
2. Human Neural Network/ Biological Neural Network
42. _______ is a subset of Machine learning.
Ans. Deep Learning
Question Answers
1. Differentiate between Supervised learning and Unsupervised learning.
Supervised Learning Unsupervised Learning
Learning from labelled data Learning from unlabelled data

Requires a labelled target variable for No labelled target variable is required

training

Predicts output based on input data Identifies patterns and relationships in the
input data

Example: Classification, Regression Example-Clustering

2. Explain Reinforcement Learning.

Ans. In Reinforcement Learning, the machine is trained to make specific decisions without
any labelled data, the machine is bound to learn from its experiences only.
The machine is exposed to an environment where it trains itself It continually using trial and
error.
3. Explain ‘Classification’ model with diagram.
Ans
1. It is a type of supervised learning.
2. It refers to a process of classify something according to
their features.
3. It classifies the given dataset (input) on the basis of related class labels.
4. It works on Discrete dataset
5. Example: Email Spam Detection

4. Explain Regression model with diagram.

Ans
1. It is a type of supervised learning.
2. These models work on continuous data to predict
the output based on patterns.
3. Example: Weather forecasting

5. Explain Clustering model with diagram.

Ans.
1. It refers to the unsupervised learning.
2. It is able to understand the dataset on its own and
perform clustering on the basis of similarities and differences
without class labels.
3. It works on discrete datasets.

6. Define the term ‘Neural Network’.

Ans.
A neural network is a computational model inspired by the human brain, composed of
interconnected nodes (neurons) that process and transmit information. It is used for various
tasks, including pattern recognition, feature extraction and image recognition by learning from
large datasets and improving their performance over time.
7. Write features/characteristics of ANN.
Ans.
1. Neural network systems are modelled on the human brain and nervous system.
2. It is made up of multiple nodes which imitate biological neurons of the human brain.
3. They are able to automatically extract features without input from the programmer.
4. It is useful to solve problems for which the datasets are very large like images, Speech
and patterns Recognition
5. Every neural network node is essentially a Machine Learning Algorithm.
6. It consists of interconnected nodes or neurons organized into layers, with each neuron
receiving input signals, processing them and passing on the output to other neurons.
8. Explain input layer of ANN.
Ans. The first layer of a Neural Network is known as the input layer. The job of an input layer
is to acquire data and feed it to the Neural Network. No processing occurs at the input layer.
9. Explain hidden layer of ANN.
Hidden layers are next to input layers. Hidden layers are the layers in which the whole
processing occurs.
Each node of these hidden layers has its own machine learning algorithm which it executes on
the data received from the input layer.
The processed output is then fed to the subsequent hidden layer of the network if available.
There can be multiple hidden layers in a neural network system and their number depends upon
the complexity of the function for which the network has been configured. Also, the number of
nodes in each layer can vary accordingly.

10. Explain output layer of ANN.

After hidden layer output layer is there. The last hidden layer passes the final processed data to
the output layer which then gives it to the user as the final output.

11. Write advantages of ANN.

Ans.
1. Fault Tolerance
2. Ability to Learn Complex Patterns
3. Adaptability
4. Parallel Processing
5. Non-linearity

12. Write Disadvantages of ANN.

Ans.
1. Hardware Dependence
2. Computational Intensity
3. Need for Large Datasets
4. Complexity and Lack of Interpretability

13. Write few applications of ANN.

Ans.
1. Signature Verification
2. Route Detection
3. Market Segmentation
4. Speech Recognition
5. Forecasting
6. Facial Recognition
7. Music Composition
8. Image Recognition
9. Pattern recognition
14. Write any two similarities between Biological Neural Networks and Artificial Neural
Networks.
1. Both ANNs and BNNs are composed of interconnected neuron-like units. In ANNs,
these units are called artificial neurons or nodes, while in BNNs, they are biological
neurons.
2. Both types of neural networks can learn from experience and adapt their behavior based
on the input they receive.
15. Explain how neural networks with diagram.
Or
Describe basic architecture of ANN with diagram.

Ans. A Neural Network consists of multiple

layers: an input layer that acquires data, hidden
layers where processing occurs, and an output
layer for the final result. Each layer contains
nodes, or neurons, which process data. The
input layer receives data, hidden layers
process it using machine learning algorithms,
and the output layer provides the final result to
the user. The number of hidden layers and
nodes varies based on the complexity of the
task. Input and output layers do not process
data; they handle data acquisition and user
interface, respectively.
16. Write short note on Perceptron.

17. Write three differences between artificial neural network(ANN) and Human neural
network (HNN).
ANN HNN
Neurons/nodes are typically arranged in Neurons in human brain are highly
layers- input, output and hidden. interconnected in a complex 3D structure.
The basic unit of ANN is a mathematical The basic unit of human brain is biological
function, referred to as a node or neuron. neuron, complex and specialized cell
ANN are designed for specific tasks and Human brain is highly flexible and
require training on relevant data. adaptable, capable of learning wide range of
tasks and generalizing knowledge to new
situations.