Unit 2 – AI Project Cycle

A. Short answer type questions:

1. What is the purpose of data exploration in the AI Project Cycle?
Ans: Data Exploration is the process of arranging / analysing the gathered data uniformly to
discover patterns and gain insights for a better understanding. In order to explore data, different
data visualisation tools like Google Charts, Tableau, Fusion Charts, High charts were used.
2. What are ANNs?
Ans: Artificial Neural Network: Modelled in accordance with the human brain, a Neural Network
was 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.
3. How do ANNs handle large database?
Ans: Neural networks can process large datasets and perform tasks, like speech recognition or
image recognition at an extremely high speed.
4. What happens in the output layer of a neural network?
Ans: The output layer receives the data from the last hidden layer and fault-tolerant to the user. It
does not process the data, but it serves as a user interface, presenting the final outcome of the
network’s computations to the user.
5. Define CNN.
Ans: Convolutional Neural Network is a Deep Learning algorithm which can take in an input
image, assign importance (learnable weights and biases) to various aspects/objects in the image
and be able to differentiate one from the other.
6. What is the significance of hidden layers in neural networks?
Ans: A hidden layer in an artificial neural network is a layer in between input layers and output
layers, where artificial neurons take in a set of weighted inputs and passes the final processed
data through last hidden layer to output layer for an active function of the model.
7. Draw the mind map for Modelling in AI Project Cycle.
B. Long answer type questions:
8. List advantages of neural networks.
Ans: Advantages of Neural networks:
 They are fast, efficient and have powerful parallel processing capacities.
 Ability to learn and enhance the performance by previous experience.
 They are highly fault-tolerant.
 Reduction of programming effort.
 They can learn from unorganised, incomplete, complex and non-linear data and produce
accurate output.
 They are flexible and can quickly change, adapt and adjust to new environments and
situations.
9. Describe the role of input, hidden and output layers in neural network.
a) A neural network consists of multiple layers, i.e., the input layer, hidden layers, and the
output layer.
b) The input layer's role is to receive data and pass it to the network without processing.
c) Hidden layers, situated between input and output layers, perform all the computation. Each
node in a hidden layer has its own machine learning algorithm, which processes data and
passes the output to the next hidden layer. This process continues until the last hidden
layer, which forwards the processed data to the output layer.
d) The output layer, like the input layer, does not process data but presents the final computed
outcome to the user. This layered structure allows neural networks to learn complex
patterns and relationships in data.
10. Neural networks are said to be modelled the way how neurons in the human brain behave. A
similar system is mimicked by the AI machine to perform certain tasks. Explain how neural
networks work in an AI model and mention any three features of Neural Networks.
Ans: Neural networks are loosely modelled after how neurons in the human brain behave. The
features of a neural network are:
1. They are able to extract data features automatically without needing the input of the
programmer.
2. A neural network is essentially a system of organizing machine learning algorithms to perform
certain tasks.
3. It is a fast and efficient way to solve problems for which the dataset is very large, such as in
images.
11. Describe the following AI models and draw an appropriate diagram:
Ans:
a) Classification:
o it is a type of supervised learning method in learning based
approach.
o uses discrete labelled datasets to predict output.
Example:
1. Email spam detector where the content, features and patterns of emails are studied
and emails are classified into authentic emails and spam.
2. To identify a trained image is correct with appropriate label

b) Regression:
 o it is a type of supervised learning method in learning based
approach.
o uses continuous labelled datasets to predict output.
Example:
1. To predict your next salary, put in the data of your
previous salary, any increments, etc., train the model.
2. Weather Prediction using past data. Here, the data which has been fed to the
machine is continuous.
c) Clustering:
o it is a type of unsupervised learning method in
learning based approach.
o uses discrete unlabelled data that can be
grouped into specific categories.
Example:
1. To predict your next salary, put in the data of your previous salary, any
increments, etc., train the model.
2. Weather Prediction using past data. Here, the data which has been fed to the
machine is continuous.
d) Dimensionality Reduction:
o it is a type of unsupervised learning method in learning based approach.
o uses unlabelled data.
o makes complex data into simple even though it comes to the cost of losing some
information.
o while reducing 3-Dimension to 2-Dimension still be able to make sense of the data.

Example:
1. Document classification
2. Image compression
e) Association:
o It is a type of unsupervised learning method in
learning based approach.
o uses large unlabelled datasets.
o involves finding relationships or patterns in
data where the occurrence of one item is
associated with the occurrence of another.
Example:
3. Market basket analysis
4. Recommender systems
5. Web usage mining.
12. Write the differences between Supervised, Unsupervised and Reinforcement learning.
Supervised Learning Unsupervised Learning Reinforcement Learning
Algorithms Algorithms Algorithms
Data provided is labeled Data provided is unlabeled The machine learns from its
data, with specified output data, the output is not environment using rewards &
values. specified, machine makes errors.
its own prediction.
Used to solve Regression Used to solve Association Used to solve Reward based
and classification and Clustering problems. problems.
problems.
Labeled data is used. Unlabeled data is used. No predefined data is used.
External Supervision. No Supervision. No Supervision.
• Solve problems by Solves problems by Follows Trail and Error
mapping labeled input to understanding patterns problem solving Approach.
known output. and discovering output.
Forecast Sales, Recommendation system, Self-driving cars, Gaming,
Risk evaluation, Email Anomaly Detection Healthcare, Parking car,
spam detector, Humanoid walking

13. Identify the type of learning (supervised, unsupervised, reinforcement learning) are the
following case studies most likely based on?
a) Case Study 1:
A company wants to predict customer churn based on past purchasing behavior, demographics,
and customer interactions. They have a dataset with labelled examples of customers who churned
and those who did not.
Ans: Supervised Learning
b) Case Study 2:
A social media platform wants to group users based on their interests and behavior to recommend
relevant content. They have a large dataset of user interactions but no predefined categories.
Which type of learning is this case study most likely based on?
Ans: Unsupervised Learning
c) Case Study 3: An autonomous vehicle is learning to navigate through a city environment. It
receives feedback in the form of rewards for reaching its destination safely and penalties for traffic
violations. Which type of learning is this case study most likely based on?
Ans: Reinforcement Learning
d) Case Study 4:
A healthcare provider wants to identify patterns in patient data to personalize treatment plans.
They have a dataset with various patient attributes but no predefined labels indicating specific
treatment plans. Which type of learning is this case study most likely based on?
Ans: Unsupervised Learning
e) Case Study 5:
A manufacturing company wants to optimize its production process by detecting anomalies in
sensor data from machinery. They have a dataset with examples of normal and anomalous
behavior. Which type of learning is this case study most likely based on?
Ans: Supervised Learning
14. Identify the type of model (classification, regression, clustering, association model) are the
following case studies most likely based on?
a) A bank wants to predict whether a loan applicant will "default" or "non-default" on their loan
payments. They have a dataset containing information such as income, credit score, loan amount,
and employment status.
Ans: Classification
b) A real estate agency wants to predict the selling price of houses based on various features
such as size, location, number of bedrooms, and bathrooms. They have a dataset containing
historical sales data.
Ans: Regression
c) A marketing company wants to segment its customer base into distinct groups based on
purchasing behavior for targeted marketing campaigns. They have a dataset containing
information such as purchase history, frequency of purchases, and amount spent.
ANS: clustering
d) A grocery store wants to identify associations between different products purchased by
customers to understand which products are commonly bought together. They have a transaction
dataset containing records of items purchased together during each transaction.
Ans: Association
15. A healthcare provider wants to improve patient care by predicting the length of hospital stays
for different medical conditions. They have a dataset containing patient demographics,
medical history, and treatment details. The task involves:
a) To predict whether a patient will have a short or long hospital stay.
ANS: Classification
b) To predict the number of days a patient will stay in the hospital.
ANS: Regression
c) To segment patients into groups with similar characteristics for personalized treatment
plans.
Ans: Clustering
d) To identify patterns in patient treatments and outcomes.
Ans: Association
Identify the type of model (classification, regression, clustering, and association model) in the
above tasks.
16. Define the following:
a) Data: Data is information in any form
b) Features: Columns of the tables are called features
c) Label: Data Labelling is the process of attaching meaning to data
d) Labelled data: Data to which some tag/label is attached.
e) Unlabelled data: The raw form of data to which no tag is attached.