NOTES FINAL EXAM 2022-23

● COGNITIVE ABILITY: The term cognitive computing is typically used to describe AI

systems that simulate human thought. Human cognition involves real-time analysis of
the real-world environment, context, intent and many other variables that inform a
person's ability to solve problems.

● PROCESS DIAGRAM OF REINFORCEMENT LEARNING:

Reinforcement learning is based on the behavioral learning model and on the basis of
interaction of the agent with the environment. The machine initially is given raw data about the
task then the agent (machine) interacts with the environment to reach the end state. The agent
 gets reward for success in the sub tasks and penalization for failure. So in a way the agent learns
from the environment and improves through trial and error methods.

● ADVANTAGES OF DATA VISUALIZATION :

Data visualization is the practice of translating information into a visual context,

such as a map or graph, to make data easier for the human brain to understand
and pull insights from. Data visualization is very critical to market research where
both numerical and categorical data can be visualized, which helps in an
increase in the impact of insights.

Advantages of Data Visualization :

1. Better Agreement: In business, for numerous periods, it happens that we

need to look at the exhibitions of two components or two situations. A
conventional methodology is to experience the massive information of both the
circumstances and afterward examine it. This will clearly take a great deal of
time.

2. A Superior Method: It can tackle the difficulty of placing the information of

both perspectives into the pictorial structure. This will unquestionably give a
superior comprehension of the circumstances.

3. Simple Sharing of Data: With the representation of the information,

organizations present another arrangement of correspondence. Rather than
sharing the cumbersome information, sharing the visual data will draw in and
pass on across the data which is more absorbable.  

4. Data Visualization Discovers the Trends in Data: The most important thing
that data visualization does is discover the trends in data. After all, it is much
easier to observe data trends when all the data is laid out in front of you in a
visual form as compared to data in a table. For example, the screenshot below
on Tableau demonstrates the sum of sales made by each customer in
descending order. However, the color red denotes loss while gray denotes
profits. So it is very easy to observe from this visualization that even though
some customers may have huge sales, they are still at a loss. This would be very
difficult to observe from a table.
5. Data Visualization Saves Time: It is definitely faster to gather some insights from
the data using data visualization rather than just studying a chart.

● REVIEWING THE SUGGESTIONS:

● EXPLAIN THE INVOLVEMENT OF MACHINE LEARNING IN NEURAL NETWORKS

A neural network is a method in artificial intelligence that teaches computers to

process data in a way that is inspired by the human brain. It is a type of machine
learning process, called deep learning that uses interconnected nodes or neurons in a
layered structure that resembles the human brain. Neural networks help us to cluster
and classify unlabelled data according to similarities among the example inputs and
deep learning maps inputs to outputs and find correlations.
● DIFFERENCE BETWEEN AI AND NEURAL NETWORKS
● DIFFERENCE BETWEEN HUMAN SYSTEM AND ARTIFICIAL NEURAL NETWORKS

● LEARNING APPROACHES USED BY NEURAL NETWORK

RULE BASED APPROACH:

Refers to AI modeling where the relationship or patterns in data are pre defined .The
algorithm just follows the rules or instructions mentioned and performs its tasks
accordingly.

Some of the features of rule-based systems are:

● They are made up of the combined knowledge of human experts in the problem
domain.
● They represent knowledge in a very declarative manner.

● They make it possible to use various knowledge representations and paradigms.

● They support the implementation of non-deterministic search and control
strategies.
● They help in describing fragmentary, ill-structured, heuristic, judgmental
knowledge.
● They are robust and have the ability to operate using uncertain or incomplete
knowledge.
● They can help with rule based decision making.

How does a rule based system in AI work?

Rule-based systems outline triggers & the actions that should follow (or are
triggered). For example, a trigger might be an email containing the word
“invoice”. An action might then be to forward the email to the finance team.
These rules most often take the form of "if" statements. "IF" outlines the trigger,
"THEN" specifies the action to complete. So, if you want to create a rule-based
system capable of handling 100 different actions, you’d have to write 100
different rules. If you want to then update the system and add actions, then you
would need to write new rules.
LEARNING BASED APPROACH :
Refers to AI modeling where the underlying relationships are not defined. In this
approach random data is fed into the machine and the algorithm needs to derive a
relationship in the data. Generally this approach is followed when the data is unlabelled
or too random for a human to make a sense out of it. The machine analyzes the data
and tries to extract similar features out of it and clusters the same data sets together. In
the end as output the machine gives us broad trends observed in the data set..as output
the machine gives us broad trends observed in the data set..

For example:
Suppose you have a set of 1000 random images of dogs, cats, cows .Now the machine
tries to recognize the similar patterns and cluster it on the basis of similarities and then
label it.
● ARTIFICIAL NEURAL NETWORKS

The term "Artificial neural network" refers to a biologically inspired sub-field of artificial
intelligence modeled after the brain. An Artificial neural network is usually a computational
network based on biological neural networks that construct the structure of the human
brain. Similar to how a human brain has neurons interconnected to each other, artificial
neural networks also have neurons that are linked to each other in various layers of the
networks. These neurons are known as nodes.

Biological Neural Network .

Artificial Neural Network

Architecture of ANN :
Input Layer:
As the name suggests, it accepts inputs in several different formats provided by the
programmer.
Hidden Layer:
The hidden layer presents in-between input and output layers. It performs all the
calculations to find hidden features and patterns.
Output Layer:
The input goes through a series of transformations using the hidden layer, which finally
results in output that is conveyed using this layer.
The artificial neural network takes input and computes the weighted sum of the inputs and
includes a bias. This computation is represented in the form of a transfer function.

● Stages involved in the evaluation process.

Evaluation is a process of understanding the reliability of any AI model, based on

outputs by feeding the test dataset into the model and comparing it with actual
answers.
 EXAMPLE :

Consider this scenario where you have an AI prediction model which predicts the
possibilities of fires in the forest. The main aim of this model is to predict whether a
forest fire has broken out into the forest or not. To understand whether the model is
working properly or not we need to predict to check if the predictions made by the model
are correct or not.

So there are two conditions:

1. Prediction
2. Reality

Prediction
The output given by the machine after training and testing the data is known as a
prediction.

Reality
The reality is the real situation or real scenario in the forest where the prediction has
been made by a machine.

Condition Prediction Reality Term

Is there a forest fire? Yes Yes True Positive

 No No True Negative

Yes No False Positive

No Yes False Negative

Condition 1 – Prediction – Yes, Reality – Yes (True

Positive)

This condition arises when the prediction and reality both match with yes (prediction –
yes, reality – yes), if forest fire has broken out.
Condition 2 – Prediction – No, Reality – No (True
Negative)

If there is no fire in the forest and prediction predicted by machine correctly as No as

well as reality also no, this condition is known as True Negative.

Condition 3 – Prediction – Yes, Reality – No (False

Positive)
There is no fire in reality but the machine has predicted yes incorrectly. This condition is known
as False Positive.

Condition 4 – Prediction – No, Reality – Yes (False

Negative)

The forest fire has broken out in reality but the machine has incorrectly predicted No
refers to False Negative condition.
Confusion Matrix
It is a comparison between prediction and reality. It helps us to understand the
prediction result. It is not an evaluation metric but a record that can help in evaluation.
Observe the four conditions explained above.

Prediction and reality can be mapped together with the help of a confusion matrix. Look
at the following:
Evaluation Methods
Now in the next section of Evaluation Artificial Intelligence Class 10, we are going to
discuss evaluation methods. These evaluation methods are as follows:

1. Accuracy
2. Precision
3. Recall
4. F1 Score

Accuracy
● The percentage of correct predictions out of all the observations is called accuracy.
● If the prediction matches with reality then it is said to be correct.
● There are two conditions where prediction matched with reality:
o True Positive
o True Negative
● So the formula for accuracy is:

The total observations cover all the possible cases of prediction that can be True
Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN).
Precision
● The percentage of true positive cases versus all the cases where the prediction is true.
● It takes into account the True Positives and False Positives.

Recall
In the recall method, the fraction of positive cases that are correctly identified will be
taken into consideration. It majorly takes into account the true reality cases wherein
Reality there was a fire but the machine either detected it correctly or it didn’t. That is, it
considers True Positives and False Negatives.
F1 score
F1 score is the balance between precision and recall.

● AI MODELLING

Definition 1:

AI modeling is the creation, training, and deployment of machine learning

algorithms that emulate logical decision-making based on available data. AI
models provide a foundation to support advanced intelligence methodologies
such as real-time analytics, predictive analytics, and augmented analytics.

Definition 2:
● Data preparation and its process .