Intro To AI

Question 1

Full formof Ai , who coined it? where

Answer 1

Artificial intelligence, John Mc carthy, darthmouth conference, 1956

Question 2

three types of Ai

Answer 2

ANI - artificial narrow intelligence, General intelligence , Super intelligence . ANI - Narrow range of abilities, focses on one task and one solution. Ex siri alexa cortana . AGI - on par with human ability.
ASI - surpasses human capabilities.

Question 3

what is intelligence

Answer 3

‘ability to perceive or infer information, and to retain it as
knowledge to be applied towards adaptive behaviours within an environment or context.’

Question 4

Mathematical
Logical Reasoning

Answer 4

•A person’s ability to regulate, measure, and understand numerical
symbols, abstraction and logic.

Question 5

Linguistic
Intelligence

Answer 5

•Language processing skills both in terms of understanding or
implementation in writing or verbally.

Question 6

Spatial Visual
Intelligence

Answer 6

•It is defined as the ability to perceive the visual world and the
relationship of one object to another.

Question 7

Kineasthetic
Intelligence

Answer 7

•Ability that is related to how a person uses his limbs in a skilled
manilr.

Question 8

Musical
Intelligence

Answer 8

•As the name suggests, this intelligence is about a person’s ability to
recognize and create sounds, rhythms, and sound patterns.

Question 9

Intrapersonal
Intelligence

Answer 9

•Describes how high the level of self-awareness someone has is.
Starting from realizing weakness, strength, to his own feelings.

Question 10

Existential
Intelligence

Answer 10

•An additional category of intelligence relating to religious and
spiritual awareness.

Question 11

Naturalist
Intelligence

Answer 11

•An additional category of intelligence relating to the
ability to process information on the environment around us.

Question 12

Interpersonal
intelligence

Answer 12

•Interpersonal intelligence is the ability to communicate with others
by understanding other people’s feelings & influence of the person.

Question 13

subsets of intelligence

Answer 13

• Ability to interact with the real world
o To perceive, understand and act
▪ Example: Speech Recognition – Understanding and synthesis
▪ Example: Image Recognition
▪ Example: Ability to take action: to have an effect

• Reasoning and planning
o Modelling the external world, given input
▪ Solving new problems, planning and making decisions
▪ Ability to deal with unexpected problems, uncertainties

• Learning and adaptation
o Continuous learning and adapting graph
▪ Our internal models are always being updated
▪ Example: Baby learning to categorize and recognise animals

Question 14

what is AI

Answer 14

When a machine possesses the ability to mimic human
traits, i.e., make decisions, predict the future, learn and
improve on its own, it is said to have artificial
intelligence.
that a machine is artificially
intelligent when it can accomplish tasks by itself -
collect data, understand it, analyse it, learn from it, and
improve it.
It is the simulation of human intelligence i.e when a machine is able to perform complex computation and logical tasks which previously could be only performed by the human brain without any interference by man.

Question 15

Applications of artificial intelligence

Answer 15

Google - it also suggests and auto-
corrects our typed sentences.
We nowadays have pocket assistants that can
do a lot of tasks at just one command.
Google mapsTo help us navigate to places, apps like UBER and Google Maps come in haman.
Thus, one no longer needs to stop repeatedly to ask for directions.
Games
This is why
platforms like Netflix, Amazon, Spotify, YouTube etc.
show us recommendations on the basis of what we
like.
They also
send us customized notifications about our online
shopping details, auto-create playlists according
to our requests and so on. Taking selfies was never
this fun as Snapchat filters make them look so
cool.
These applications are not limited to smart devices but
also vary to humanoids like Sophia, the very first
humanoid robot sophisticated enough to get
citizenship, biometric security systems like the face
locks we have in our phones, real-time language
translators, weather forecasts,

Question 16

What is not AI?

Answer 16

A fully automatic washing machine can work on its own, but it requires human
intervention to select the parameters of washing and to do the necessary preparation for
it to function correctly before each wash, which makes it an example of automation, not
AI.
An air conditioner can be turned on and off remotely with the help of internet but still
needs a human touch. This is an example of Internet of Things (IoT). Also, every now and
then we get to know about robots which might follow a path or maybe can avoid
obstacles but need to be primed accordingly each time.
We also get to see a lot of projects which can automate our surroundings with the
help of sensors. Here too, since the bot or the automation machine is not trained with
any data, it does not count as AI.

Question 17

What is Machine learning

Answer 17

It is a subset of Ai .
It helps the machine to work intelligently and take decisions from their experiences.
The machine is learning by itself and making predictions. In this machine uses mathematical model which uses the samplw data known as training data . It gains inferences from patterns in data

Question 18

Examples of ML

Answer 18

Netflix Prime to predict likes and suggestions.
Email filtering computer vision.Personalised recommendations from online shopping sites.

Question 19

Classifications of ML

Answer 19

Superivised algo.
- classification
-regression
Unsupervised algo.
-clustering
-reinforcement learning

Question 20

DL

Answer 20

It is a subset of Machine learning which helps the machine to take deicions and learn from larde datasets,
The info is processed on a large amount of data entered just like the human brain identifies patterns basen on various information . The new data set is compared with the old dataset to make sense out of it.
It imitates the way humans gain knowledge

It enables software to train itself to perform tasks with vast amounts of 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 out of these three. Then comes Machine Learning which is intermediately intelligent and Artificial Intelligence covers all the concepts and algorithms which, in some way or the other mimic human intelligence.

Question 21

Classifications of DL

Answer 21

SUPERVISED , SEMISUPERVISED , UNSUPERVISED

Question 22

Relation between AI , ML , DL

Answer 22

AI - ML - DL

Question 23

Applications of Dl

Answer 23

Dl can also be called - Deep neural network . Can be applied in the fields of Nlp , board gme , speech recognition and imgae processing.

Question 24

Three parts of Ai

Answer 24

THE THREE PARTS OF AI ARE -
1)DATA SET is a collection of data which can be in any form - numbers characters , letters , images , video , and audio, even views.
2) An ALGORITHM, - it is a set of instructions which follows the IPO ( input -processing-output) cycle in order to do a task.
3)The PREDICTION is the probability of outcomes that could arise when an algorithm is executed.

Question 25

Difference between classification and regression

Answer 25

Classification problems use statistical classification methods to output a categorisation .
Regression problems on the other hand - use statistical regression analysis to provide numerical outputs
Regression algorithms are used to predict the continuous values
Classification algorithms are used to predict/Classify the discrete values s

Question 26

What is training data

Answer 26

it is entered into the machine which is used by the algorithm as a reference to predict the output. Training data is the data you use to train an algorithm or machine learning model to predict the outcome you design your model to predict. Test data is used to measure the performance, such as accuracy or efficiency, of the algorithm you are using to train the machine.

Question 27

Testing data

Answer 27

is used to check the efficiency of the machine/model to be deployed.

Question 28

Diference between supervised and unsupervised learning

Answer 28

suspervised learning algorithms learn from a dataset which is labelled.
while unsupervised learning algorithms makes sense by extracting features /patterns from the unlabelled dataset.

Question 29

Reinorcement learning

Answer 29

It works towards accomplishing a task and tries to improve the performance in a particular task. This algorithm is used in gaming.

Question 30

K-W-L-H

Answer 30

K• What I Know?
W • What I Want to know?
L• What have I learned?
H• How I learnt this?