Scribd
Upload
28 views4 pages

Introduction To Ai

The document provides an overview of Artificial Intelligence (AI), detailing its history, applications, and the distinction between conventional programming and machine learning (ML). It explains that ML is a subset of AI that enables machines to learn from data, and discusses various types of data and learning methods. Additionally, it highlights the structure of neural networks and the emerging field of deep learning, along with potential job opportunities in AI.

Uploaded by

sanjudxbreddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
28 views4 pages

Introduction To Ai

The document provides an overview of Artificial Intelligence (AI), detailing its history, applications, and the distinction between conventional programming and machine learning (ML). It explains that ML is a subset of AI that enables machines to learn from data, and discusses various types of data and learning methods. Additionally, it highlights the structure of neural networks and the emerging field of deep learning, along with potential job opportunities in AI.

Uploaded by

sanjudxbreddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

INTRODUCTION TO AI

History of AI
AI is defined as the ability of a machine to mimic human traits, i.e, make decisions, predict
the future, learn and improve on its own. It was first coined by John McCarthy at the
Dartmouth conference of 1956.

In 1950’s: Alan Turning introduced “Turning Test” for assessment of intelligence.


In 1955: John McCarthy known as the founder of Artificial Intelligence introduced the term
‘Artificial Intelligence’.
In 1970’s: These machines were much quicker, affordable and stowed more information.
Had an amazing character to think abstract, could self-recognize and accomplished nlp.
In 1980’s: Saw flow of funds for research and algorithmic tools. The learning skills were
enhanced and computers improved with deeper user experience.
In 2000’s: Milestones were achieved despite of lack of government funds and public
appreciation.

Applications
1. Gmail: automatically separating emails as ‘Spam’ and ‘Not Spam’. Spam emails being
automatically sent to the Spam folder saves a lot of your time.
2. YouTube: suggests vids to view based on your search history and past view history.
3. Flipkart or Amazon: advised to purchase products of your choice.
Difference between conventional programming and ML
 Their approaches and goals are different

CONVENTIONAL PROGRAMMING
A human programmer creates the programme by hand. Since the logic is not programmed,
rules must be manually coded.
Eg:

MACHINE LEARNING
The input data and the output data are fed to an algorithm to create a program. Machine
Learning is an automated process where a programmer feeds the computer with ‘The Input +
The Output’ and computer generates the algorithm as to how the ‘The Output’ was achieved.
Eg:

How is ML related to AI?


It is a subset of AI and enables machines to improve at tasks with data. It is used to enable
machines to make predictions themselves. Machine learning enables machines to learn
forecast and advance on their own.

Features
 Virtual Personal Assistant : Siri, Alexa
 Video Surveillance
 Social Media Services
 Filtering of email spam and viruses
 Product recommendations,
 Online Fraud Detection

Data
Representation of info that can be processed by machines / humans. Basically, a simple
representation of something.
TYPES:
Structured Data: Quantitative data. Contains data types and formats that make it easy to
insert into database columns and spreadsheets fields. Well organised and simple to
understand. Eg: name, age, address.
Unstructured Data: Qualitative data. Cannot be analysed using traditional database
techniques. Eg: text, audio, video, social media activity, surveillance.

TYPES:
Supervised Learning
Requires labelled data sets. Data is classified according to labels. Data is continuous.
Unsupervised Learning
Unlabelled datasets. Recognized patterns and trends. Groups unknown data according to
patterns and trends. No feedback.
Reinforcement Learning
Reward punishment method. Desired process. Act and learn by making mistakes.

Neural network
 It is a technique that instructs computers to analyse data in a manner modelled after
human brain and human nervous system.
 They are able to automatically extract features without input from the programmers.
 Every Neural Network node is essentially a machine learning algorithm.
 It is useful when solving problems for which the data set is very large.

LAYERS
1) Input Layer : acquire data and feed it to the neural network. no processing takes place.
2) Hidden layer : all the processing takes place here. has nodes, and each node has its own
machine learning algorithm.
3) Output Layer: Displays the output for the user. no processing takes place here.
ANN(ARTIFICAL NERUAL NETWROKS): Layers of computer programme components
called neurons/nodes. Until all the data is categorized, these networks transform the data from
one neuron to another.
Deep Learning
Uses large amounts of data. such machines can develop algorithms for themselves. most
advanced form of AI.
Examples: Automated Driving: detect objects, recognize pedestrians, Aerospace and defence,
medical research: cancer cells identification

Jobs In AI
 Data Analytics
 Research scientist
 Researcher
 Ai engineer
 Software engineer
 Data scientist
 Big data architect

You might also like