Revisiting AI Project Cycle class 10 notes

The overview of the six stages of the AI Project Cycle

If we have to develop an AI project, the AI Project Cycle provides us with an
appropriate framework which can lead us towards the goal. Definition: The AI
Project Cycle is a step-by-step process that a company must follow in order to
derive value from an AI project and to solve the problem.

The AI Project Cycle mainly has 6 stages:

• Step 1: Problem Scoping: In Problem Scoping we try to find the

problem; we look at various parameters which affect the problem we
wish to solve so that the picture becomes clearer.
• Step 2: Data Acquisition: You need to acquire data which will
become the base of your project, data can be collected from various
reliable and authentic sources.
• Step 3: Data Exploration: The data you collect would be in large
quantities, you can try to give it a visual image of different types of
representations like graphs, databases, flow charts, maps, etc. This
makes it easier for you to interpret the patterns which your acquired
data follows.
• Step 4: Modeling: After Exploration you have to decide which type
of model you would build to achieve the goal. For this, you can
research online and select various models which give a suitable
output.
• Step 5: Evaluation: Once the modelling is complete, you now need
to test your model on some newly fetched data. The results will help
you in evaluating your model and improving it.
• Step 6: Deployment: Finally, after evaluation, the deployment stage
is crucial for ensuring the successful integration and operation of AI
solutions in real-world environments, enabling them to deliver value
and impact to users and stakeholders.
Introduction to AI Domains
Depending on the type of data, we can divide AI into different domains:

1. Statistical Data
2. Computer Vision
3. Natural Language Processing
1. Statistical Data
Statistical Data is a domain of AI related to data systems and processes, in which
the system collects numerous data, maintains data sets and derives
meaning/sense out of them. The information extracted through statistical data
can be used to decide about it.

Example of Statistical Data

Price Comparison Websites – Price comparison websites comparing the price

of a product from multiple vendors in one place. for example, PriceGrabber,
Racerunner, Junglee, Shopzilla, DealTime. Nowadays, price comparison
websites can be found in almost every domain such as technology, hospitality,
automobiles, durables, apparel, etc.

2. Computer Vision
Computer Vision is an AI domain works with videos and images enabling
machines to interpret and understand visual information and afterwards predict
some decisions about it. The entire process involves image acquiring, screening,
analyzing, identifying and extracting information.

Examples of Computer Vision

Agricultural Monitoring – Computer vision is employed in agriculture for crop

monitoring, pest detection, and yield estimation. Drones with cameras capture
aerial images of farmland, which are then analysed to assess crop health and
optimize farming practices.

Surveillance Systems – Computer vision is used in surveillance systems to

monitor public spaces, buildings, and borders. It can detect suspicious activities,
track individuals or vehicles, and provide real-time alerts to security personnel.
3. Natural Language Processing
Natural Language Processing is a branch of artificial intelligence that deals with
the interaction between computers and humans using the natural language. The
objective of NLP is to read, decipher, understand, and make sense of human
languages in a valuable manner.

Examples of Natural Language Processing

Email filters – Email filters are one of the most basic and initial applications of
NLP online. It started with spam filters, uncovering certain words or phrases that
signal a spam message.

Machine Translation – NLP is used in machine translation systems like Google

Translate and Microsoft Translator to automatically translate text from one
language to another.

Ethical Frameworks for AI

What do you mean by Frameworks in AI?

Frameworks are a set of steps that help us in solving problems. It provides a
step-by-step guide for solving problems in an organized manner. Moreover,
frameworks offer a structured approach to problem-solving, ensuring that all
relevant factors and considerations are taken into account.

What do you mean by ethical frameworks in AI?

The ethical framework of artificial intelligence helps to guide the development
and design of AI systems to ensure that they are following ethical principles and
values.

Definition: Ethical frameworks provide a systematic approach to navigating

complex moral dilemmas by considering various ethical principles and
perspectives.

To design an ethical AI system, the following things are to be followed:

• AI systems should respect user rights.

 • AI systems should be safe and fair.
• AI system should protect user privacy.
• AI systems should be transparent.
Why do we need Ethical Frameworks for AI?
Ethical frameworks ensure that AI makes morally acceptable choices. If we use
ethical frameworks while building our AI solutions, we can avoid unintended
outcomes, even before they take place!

Types of Ethical Frameworks

Ethical frameworks for AI can be categorized into two main types: sector-based
and value-based frameworks.

1. Sector-based Frameworks:

one common sector-based framework is Bioethics, which focuses on ethical

considerations in healthcare. It addresses issues such as patient privacy, data
security, and the ethical use of AI in medical decision-making. Sector-based
ethical frameworks may also apply to domains such as finance, education,
transportation, agriculture, governance, and law enforcement.

2. Value-based Frameworks:

Value-based frameworks focus on fundamental ethical principles and values

guiding decision-making. Value-based frameworks are concerned with assessing
the moral worth of actions and guiding ethical behaviour. They can be further
classified into three categories:

• Rights-based: In the context of AI, this could involve ensuring that

AI systems do not violate human rights or discriminate against
certain groups.
• Utility-based: Evaluates actions based on the principle of
maximizing utility or overall good, aiming to achieve outcomes that
offer the greatest benefit and minimize harm. For example, job
displacement or privacy concerns.
• Virtue-based: This framework focuses on the character and
intentions of the individuals involved in decision-making. In the
context of AI, virtue ethics could involve considering whether
developers, users, and regulators uphold ethical values throughout
the AI lifecycle.
What do you mean by bioethics framework in healthcare
industry?

The bioethics framework is used in medicine, health, and science. A bioethics

framework is a set of principles and rules that help machine to make ethical
decisions in healthcare. It helps to address complex issues in healthcare and in
the health-related research.

Principles of bioethics:

• Respect for Autonomy.

• Do not harm.
• Ensure maximum benefit for all.
• Give justice.

What are the main principles of AI ethical should be consider for making AI
application?

There are three main principles that should be followed whenever developing an
AI application:

• Non-maleficence – non-maleficence refers to the ethical principle of

avoiding causing harm or negative consequences.
• Maleficence – Maleficence refers to the concept of intentionally
causing harm or wrongdoing.
• Beneficence – Beneficence refers to the ethical principle of
promoting and maximizing the well-being and welfare of individuals
and society.
Case Study

Let’s see one case study. Suppose a company wants to design an AI algorithm
for optimizing patient care. The objective of the development of the AI algorithm
is to help doctors to make better decisions and identify high-risk patients, but due
to unintended biases and due to inaccurate data, the AI algorithm makes
mistakes due to unfair patterns in the data, which increases the patient risk levels
and can compromise patient health. This issue has to be fixed; otherwise, it can
affect patient health.

How the ethical problem can be solved?

The four principles of bioethics can be used to ensure an ethical AI solution for
the healthcare problem.

• Respect for autonomy: Enabling users to be fully aware of

decision-making. E.g., users of an AI algorithm should know how it
functions.
• Do not harm: Harm to anyone (be it human or non–human) must be
avoided at all costs. If no choice is available path of least harm must
be always chosen.
• Maximum benefit: Not only should we avoid harm our actions must
focus on providing the maximum benefit possible.
• Justice: All benefits and burdens of a particular choice must be
distributed in a justified manner across people irrespective of their
background.
Advance Concepts of Modeling in AI class 10 notes
Artificial intelligence (AI) is the ability of machines to do cognitive tasks such as thinking,
perceiving, learning, problem-solving, and decision-making. ML and DL is a subset of
Artificial Intelligence.

Differentiate between AI, ML, and DL

Artificial Intelligence Machine Learning Deep Learning

ML is a subset of AI,
AI can simulate human DL is a subset of ML that
which uses
intelligence to perform the uses artificial neural
algorithms to learn
task. networks for complex tasks.
patterns from data.

ML depends on
DL requires large, labeled
AI has predefined rules. labeled data for
data to perform tasks
making predictions

ML can learn
AI can be rule-based and DL automates feature
automatically with
require human extraction and lessens
less human
programming human intervention
intervention

AI is used in virtual
ML is used in spam DL is used in speech
assistants,
filtering, image recognition, autonomous
recommendation systems,
recognition, etc. vehicles, etc.
etc.

Artificial Intelligence

Artificial intelligence (AI) is the simulation of human intelligence in robots that have been
trained to think and act like humans. The term can also refer to any machine that
demonstrates, like humans, the ability to learn and solve the problem is Artificial
Intelligence.
Machine Learning (ML)

Machine learning is a part of an Artificial Intelligence application in which we give data to

the machine and allow them to learn for themselves. It’s essential getting a machine to
accomplish something without being specifically programmed to do so. The machine
learns from its mistakes and takes them into consideration in the next execution. It

improvises itself using its own experiences.

Here is an example which shows labelled images (every image is tagged either as apple or
strawberry) are given as input to the ML model. ML model learns from the input data to
classify between apples and strawberries and predicts the correct output as shown.

Examples of Machine Learning (ML)

• Object Classification – Object classification refers to the process of identifying and

categorizing specific objects within an image or video. For example, there is an
image with multiple animals; if you want to categorize or identify a specific animal,
then it is only possible with machine learning.

• Anomaly Detection – Anomaly detection helps us find the unexpected things hiding
in our data. For example, tracking your heart rate, and finding a sudden spike could
be an anomaly, flagging a potential issue.

Deep Learning (DL)

Deep learning is a part of Artificial Intelligence that uses neural networks with multilayer.
Deep learning analyzes the data, learns the data and solves the problem the same as a
human. Deep learning requires the machine to be educated with a large quantity of data in
order to train itself. Deep Learning is the most advanced form of Artificial Intelligence out of
these three.

Here is an example which shows pixels of a bird image given as input to the DL Model and
the model is able to analyze and correctly predict that it is a bird using a deep learning
algorithm (ANN).

Examples of Deep Learning (DL)

• Object Identification – Object classification in deep learning tackles the task of

identifying and labeling objects within an image. It essentially uses powerful
algorithms to figure out what’s in a picture and categorize those things.

• Digit Recognition – Digit recognition in deep learning tackles the challenge of

training computers to identify handwritten digits (0-9) within images.

Common terminologies used with data

What is Data?

Data is information in any form. For e.g. A table with information about fruits is data. Each
row will contain information about different fruits. Each fruit is described by certain
features.
What do you mean by Features?

Columns of the tables are called

features, In the fruit dataset example,
features may be name, color, size, etc.,
Some features are special, they are
called labels.

What are Labels?

Data Labeling is the process of attaching meaning to data. For e.g. if we are trying to predict
what fruit it is based on the color of the fruit, then color is the feature, and fruit name is the
label.

Data can be of two types – Labeled and Unlabeled

What are Labeled Data?

Data to which some tag/label is attached is known as labeled data. For example, name,
type, number, etc. Unlabeled data is a raw form of data that has no tag attached.

What do you mean by a training data set?

The training data set is a collection of examples given to the model to analyze and learn.
Just like how a teacher teaches a topic to the class through a lot of examples and
illustrations. Similarly, a set of labeled data is used to train the AI model.

What do you mean by a testing data set?

The testing data set is used to test the accuracy of the model. Just like how a teacher takes
a class test related to a topic to evaluate the understanding level of students. Test is
performed without labeled data and then verify results with labels.

Modelling

AI Modelling refers to developing algorithms, also called models which can be trained to
get intelligent outputs. An AI model is a program that uses algorithms to analyze data and
make decisions without human intervention. AI models are trained on data sets to
recognize patterns and perform tasks.

There are two different approaches in AI models

• Rule Based Approach

• Learning Based Approach

Rule Based – Rule Based AI modelling where the rules are defined by the developer. The
machine follows the rules or instructions mentioned by the developer and performs its task
accordingly. For example, Rule-based Chatbots are commonly used on websites to answer
frequently asked questions (FAQs) or provide basic customer support.

A drawback of the rule-based approach

• In a rule-based approach, the learning is static.

• Once trained, the machine will not make any changes in the training dataset.
 • If you try testing the machine on a dataset which is different from the rules and data
you fed it at the training stage, the machine will fail and will not learn from its
mistake.

• Once the model is trained, the model cannot improvise itself on the basis of
feedback.

• In a rule-based model, it does what it has been taught once.

Learning Based – Refers to the AI modelling where the machine learns by itself. Under the
Learning Based approach, the AI model gets trained on the data fed to it and then is able to
design a model which is adaptive to the change in data. Random data is provided to the
computer in this method, and the system is left to figure out patterns and trends from it.

The learning-based approach can further be divided into three parts:

1. Supervised Learning

2. Unsupervised Learning

3. Reinforcement Learning

1. Supervised Learning

Supervised learning is a machine learning technique that uses labeled data to train
algorithms to predict outcomes. In a supervised learning model, the dataset which is fed to
the machine is labelled. In other words, we can say that the dataset is known to the person
who is training the machine only then he/she is able to label the data.

Supervised Learning – Example

Let’s consider the example of currency coins. Problem Statement: Build a model to predict
the coin based on its weight. Assume that we have different currency coins (dataset) having
different weights. 1 Euro weighs 5 grams, 1 Dirham weighs 7 grams, 1 Dollar weighs 3
grams, 1 Rupee weighs 4 grams and so on.

• Feature – Weights,

• Label – Currency

So, if a model is trained in tagging the features i.e., the weights of the coin with the targets
i.e., currency, the trained model can be further used to identify a coin based on its weight
(since it has already been learnt).

There are two types of Supervised Learning models:

a. Classification

Where the data is classified according to the labels. For example, in the grading system,
students are classified on the basis of the grades they obtain with respect to their marks in
the examination. This model works on discrete dataset which means the data need not be
continuous.

Examples of the Classification Model

Classifying emails as spam or not: The model is

shown tons of emails, both real ones (like from
friends or colleagues) and spam. The model learns
what makes an email look like spam. Once
trained, the model sees a new email. It analyzes
the clues in the email and decides: is this spam or
not? It assigns a category – “spam” or “not spam” –
just like sorting your mail.

b. Regression
Such models work on continuous data. For example, if you wish to predict your next salary,
then you would put in the data of your previous
salary, any increments, etc., and would train the
model. Here, the data which has been fed to the
machine is continuous.

Examples of the Regression Model

Predicting temperature: Temperature is a

continuous variable, meaning it can take on any
value within a range. Regression models are well-
suited for predicting continuous outputs.

Used Car Price Prediction: This model predicts

the selling price of the car with the help of a few
parameters like
fuel type, years of service, the number of previous
owners, kilometers driven, transmission type (manual/automatic). This type of model will
be of type regression since it will predict an approximate price (continuous value) of the car
based on the training dataset.

2. Unsupervised Learning

An unsupervised learning model works on unlabeled dataset. This means that the data
which is fed to the machine is random and there is a possibility that the person who is
training the model does not have any information regarding it. It helps the user in
understanding what the data is about and what are the major features identified by the
machine in it.

Unsupervised Learning – Example

Assume that we have a customer database with records of their products bought over a
period. Now you being the marketing manager decides to send a grocery offer message to
those customers who buys grocery regularly. Model could discover patterns on its own and
could come up with two different group a) Grocery Shopper and Non-grocery Shopper.

Unsupervised learning models can be further divided into two categories:

a. Clustering

Refers to the unsupervised learning algorithm which can cluster the unknown data
according to the patterns or trends identified out of it. The patterns observed might be the
ones which are known to the developer, or it might even come up with some unique
patterns out of it.

What is the difference between Clustering and Classification?

• Classification uses predefined classes in which objects are assigned.

• Clustering finds similarities between objects and places them in the same cluster
and it differentiates them from objects in other clusters.

b. Association

Association is another type of unsupervised learning method that uses different rules to
find relationships between variables in a given data set. This is a data mining technique
used for better understanding of customer purchasing patterns based on relationships
between various products.

Example:

Based on the purchase pattern of customers A and B, can you predict any Customer X who
buys bread will most probably buy? Based on the purchase pattern of other customers, we
can predict that there is high probability that any customer x who buys bread will most
probably buy butter. Therefore, such meaningful associations can be useful to recommend
items to customers. This is called Association Rule.

3. Reinforcement Learning

This learning approach enables the computer to make a series of decisions that maximize a
reward metric for the task without human intervention and without being explicitly
programmed to achieve the task. It’s based on a trial-and-error learning process to achieve
 the goals. Examples of reinforcement learning are question and answering, machine
translation, and text summarization.

Reinforcement Learning – Example

Reinforcement learning is a type of learning in which a machine learns to perform a task

through a repeated trial-and-error method. Let’s say you provide an image of an apple to
the machine and ask the machine to predict it. The machine first predicts it as ‘cherry’ and
you give negative feedback that it’s incorrect. Now, the machine learns that it’s not a cherry.

Then again, you ask the machine to predict the fruit by giving an image of an apple as input;
Now, it knows it is not a cherry. It predicts it as an apple, and you give positive feedback
that it’s correct. So, now the machine learns that this is an apple.

Difference between supervised and unsupervised Learning?

Supervised Learning Unsupervised Learning

Deals with labelled data Deals with unlabeled data

Useful in real-world problems like

Useful in finding unknown patterns within data like making sense of a
predicting the prices of an item are
large number of observations from an experimental device.
something based on past trends.

Computing power required is simpler as The computing power required is more complex as unsorted and
clean labelled data is used as input. messy data is used as input
Summary of ML Models

• Supervised learning models are used when we want to determine relationships

through training.

• Unsupervised learning models are used when we want to discover new patterns
from data.

• Reinforcement learning models are used when we want to implement machine

learning through a reward mechanism.

Sub-Categories of Deep Learning

Deep learning is a subset of machine learning that uses artificial neural networks to learn
from data. In deep learning, the machine is trained with huge amounts of data, which helps
it in training itself around the data. Such machines are intelligent enough to develop
algorithms for themselves. Deep learning is the most advanced form of artificial
intelligence.

Subcategories of Deep Learning:

1. Artificial Neural networks (ANN)

2. Convolutional Neural Network (CNN)

1. Artificial Neural networks (ANN)

What is Neural Network?

Neural networks are modelled on the human brain and nervous system. They are able to
automatically extract features without input from the programmer. Every neural network
node is essentially a machine learning algorithm. It is useful when solving problems for
which the data set is very large.

How neural networks work:

An artificial neural network is a type of machine learning algorithm derived from biological
neural network principles that can work similarly to the human brain using neuron
interconnection. These neurons are known as nodes. An artificial neural network has an
input layer, an output layer, and hidden layers. The input layer is responsible for receiving
the data from the real world, and all the input data passes through one or multiple hidden
layers and transforms the result using the output layer.

The structure of an entire artificial neural network consists of

• Input layer – takes input data and transfers it to the hidden layer of neurons using
synapses.

• Hidden layer – takes data from the input layer to categorize the data and send it to
more hidden layers and finally send it to the output layer.

• Output layer – takes the data from the hidden layer and generates the result.

How do Artificial Neural Networks learn?

Artificial neural networks are trained

using a training set. For example,
suppose you want to teach an ANN
to recognize a dog; using the input
layer, thousands of different dog
images will be shown to the neural
network. Once the neural network is
trained, then ANN will help to
identify whether the neural network
has identified the dog correctly or not. When output is generated, then ANN will verify the
dog image against the human-provided description. If the ANN finds it incorrect, then
backpropagation is used to adjust the image during the training. This process continues
until the ANN can correctly recognize a dog in an image.
How does AI make a Decision?

Let's say you want to go out to the park today. What would be your thought
process? What would you consider?

Most of us would want to avoid getting soaked in the rain. These are possible
factors that may influence your decision whether to go out.

So, the first question that you may ask is, “Should I bring a rain jacket?” Then, you
may also ask, “Should I bring an umbrella?” Or you may also ask, “What is the
weather now?” And finally, “What will the weather be like, later in the day?”

Now, you have the factors that will influence your decision to go out. But take note,
not all factors are equal. Some factors are more important, while some are not.
Let's see which one is more important. Let us rank them from the most important to
the least important.
For me, “is it sunny now” is more important than “the weather forecast later”. And
“having a jacket” is more important than “having an umbrella.” We can put the
ranking for this example.
Now let us convert this to perceptron.
Going back to the earlier example, we have four inputs. So, let’s draw the
perceptron with four inputs (from X1 to X4). Next, we have their weights (from W1
to W4). Then, we also have bias B, with weight WB.
Finally, we sum them all up, compared with threshold, and we will get our output.
The values for the weights can come from experience. He may have an experience
of being sunny now would most likely mean a bright day ahead, hence the high
importance there. It can also come from personal preference. A person may judge a
particular factor more heavily as compared to another person. For example, she
may be more concerned with the weather forecast, hence the higher importance
there.

The values for WB are also based on personal preference. If a person is more
cautious, he may set the value for WB to be higher, hence his decision would gear
towards staying indoors unless he is sure that it would not rain. On another hand, a
person who is more daring will have a lower WB; hence he is more likely to go out
regardless of the current situation. In this example, we choose 4 as we want to be
more cautious.

Therefore, there is no right or wrong answers in coming up with the values for the
weights. However, the effects of the values will determine the outcome that the
person is going to take, whether to go out or not. That is the reason why everyone
comes up with a different decision, even though the situation is the same for
everyone.
For this example, let’s say: I have a jacket, I don’t have an umbrella, it is sunny now,
and the weather forecast is going to rain. We can convert the yes and no to numbers
1 and 0. For bias, we will always take 1.

From this calculation, the output is 0.5. Since this is higher than the threshold
(which is zero), the result is I will go out to the park.