Page 6 - Artificial Intellegence_v2.0_Class_9
P. 6
INSIDE THE SERIES
For example: orangebooks@gmail.com
authors_orange@hotmail.com
anjana.shalini@outlook.com
myaccount@orangeeducation.in
The key features of the series have been designed to ensure better
Structure of an Email Message
learning and assessment. Following are the major sections of an email message:
• Header: This section allows you to enter the following information:
✶ From: Email address of the sender.
✶ To: email address of the recipient.
Learning Resources ✶ Cc (Carbon Copy): This option is generally used when we want the same message to be sent to a large group
of people at the same time. The list of all the recipients will be displayed in the received message header. We
can also use this option when we want another person to be informed of the mail sent to the recipient.
✶ Bcc (Blind Carbon Copy): This Email address is invisible to a recipient. This option is used when you want to
send a copy of an email to another person without bringing it to the knowledge of the recipient. It will not be
displayed in the received message header.
UNIT-3 ✶ Subject: It is the brief discussion of the topic of the message.
Brainy Fact:
Learning Outcomes: • Body: This is the actual content of the email written by the sender. It consists of the message and the signature
NEURAL NETWORKS
of the sender.
It presents an interesting fact relevant
It provides an overview of the • Attachments: We can attach any type of file like word document, presentation, any program code, audio, video
unit/chapter contents. etc. It is usually a symbol of a paper pin. Select this option to open a dialog box which gives access to files stored
to the topic or the chapters.
in your device. Select a proper path to attach the required file.
• Date: It is the date and time of sending a message. Communication
Learning Outcomes
Brainy Fact
Balloon Debate
• Why do we use Neural Networks? • Applications of Neural Networks Say: “We are going to debate about the boon and bane of various AI applications in the different
The first email was sent in 1971. Ray Tomlinson, the engineer who invented the email program on
• Advantages of Neural Network • AI Models industries you researched about. This will be a 4 v 4 debate. As you know, each theme has been
• Human Nervous System • Relation between the Neural Network and Nervous System given to two different teams. Now one team out of these two with be in affirmation with AI
the ARPANET system.
• Working of Neural Networks • Types of Neural Networks applications in their theme while the other one will be against AI applications in the same theme.
Data The debate will go theme by theme wherein each member of the team will get a minute to speak.
Neural networks form a base of deep learning, a subfield of machine learning where algorithms are inspired by The first speaker of the affirmative team will start the debate after which the first speaker of the
Creating an Email Account
the structure of the human brain. Neural networks take input data, train themselves to recognise the patterns
Data is a domain of AI that is related to input to the AI machine. Under rebuttal team will put their points. In this manner, each speaker will get a minute to speak and
in this data and then predict the output for a new set of similar data. The most impressive aspect of neural
Before we get into this process of sending and receiving an email, it is important to create an email account. Either
this domain, the type of input data can be numeric (0–9) or text (A–Z or finally one team will be chosen to be thrown out of the balloon debate depending upon how
networks is that once trained, they learn on their own just like human brain.
convincing their points were. The speaker who speaks more than a minute will get his team
we can have a paid email service by creating an email using an ISP server or we can create an email account by using
a–z) or special symbols (#, @, $, etc.). More the data, the better will be disqualified. You will get 15
Why do we use Neural Networks?
AI Game: minutes to prepare your points. And your time starts now!”
the analysis and more accurate would be the prediction. Thus, AI requires
a free web based email service provider. Some of the commonly used are: Hotmail.com, Gmail.com, Outlook.com,
Yahoo.com, rediffmail.com etc. You can write the email address of any of these in the address bar of any browser
large amounts of data to find the latest trends and patterns. For example, data is then fed to the subsequent hidden layer. There can be multiple hidden layers depending
Neural networks are a series of algorithms used to recognise hidden patterns in raw data, cluster and classify it,
Imagine there are two families of four people out for a ride in a hot air balloon. Suddenly the
balloon starts to move towards the earth instead of staying airborne. To stabilize it, one family upon the
At a Glance:
It contains an interesting game or activity complexity of the function to be performed by the model. The processed data by the hidden layers is passed
window. Let us now proceed to create an email account in the Gmail email service:
continuously learn and improve. They are used in a variety of applications in stock markets, sales and marketing trends,
I plan to organise a social gathering in an open-air setup in the month of
risk assessment and fraud detection. The main advantage is that the data features can be extracted automatically by
needs to take the parachute and go out of the balloon or else it will come crashing down.
August in Delhi. I will have to look for a weather forecast for the same and onto the output layer which then gives the final output to the user. No processing is done in the output layer.
Step 1 Connect your computer to the Internet and type www.gmail.com in the address bar browser window. It
the machine without the input from the developer. Neural networks are primarily used for solving problems with large
This section provides a summary
Who should be thrown out of the hot air balloon?
for the students to try on their own or with will display the following screen:
datasets, like images. To summarize the need to use neural networks:
also look at the previous years' trends. So, data collection is the base for
Machine Learning
analyses and pattern recognition models. From those patterns, predictive Step 2 Click on Create account option. Machine Learning
of the chapter.
their classmates to learn how the game Data Algorithm + Hidden Rules Algorithm + Hidden Rules Answer
Large Neural Network
models can be made.
Model Performance
Medium Neural Network
Touchpad Artificial Intelligence (Ver. 2.0)-IX
So, the data is the most important part of an AI machine. After the data is collected from different sources, the
mechanics work while having fun. At a Glance Algorithm + Hidden Rules Answer
86
Small Neural Network
AI machine analyse the data and then process it.
Traditional Machine Learning Algorithms
Machine Learning
Machine Learning
Data
Algorithm + Hidden Rules
machines, especially in computer systems, so that they can think and perform actions similar to humans.
GAME 01 Rock Paper and Scissors Experiential Learning • Artificial Intelligence (AI) is a branch of computer science that simulates human intelligence into
Size of Data • Machines are fed with enough data and correct algorithms to make them intelligent.
Machine Learning
Data
• Every automated gadget around us is not necessarily AI based. Machine Learning Answer
• It can extract data features automatically without the input from the developer. Algorithm + Hidden Rules Algorithm + Hidden Rules
• It is fast and efficient way to solve problems with large datasets, such as images. • The modern-day AI came into existence in the 1950s when Alan Turning introduced the “Turing Test”
for assessment of intelligence.
• It is essentially a system of machine learning algorithms to perform certain tasks. • Human-machine interaction (HMI) can be defined as the communication or interaction between
• The larger neural networks tend to perform better with larger amounts of data whereas the traditional machine humans and machines through a user interface to fulfill a specific task or operation.
learning algorithm stops improving after a certain saturation point. See the figure: • Types of Neural Networks
Artificial Intelligence is composed of three domains which are Data, Computer Vision and Natural
Language Processing.
Neural Networks 255 There are mainly two types of Neural Networks:
• Artificial Neural Network
Data is a domain of AI that is related to data input to the AI machine.
•
•
Computer Vision (CV) is the domain of Artificial Intelligence that is used to train computers to read,
• Biological Neural Network
process and analyse visual data in the same way as humans do.
Now let us learn about them in detail.
•
NLP gives the ability to machines to read, understand and analyse meaning from human language.
• Smart Living is a trend that improves our living standards and allows people the to take benefit from
new ways of living.
Artificial Neural Networks (ANN)
•
In 2015, the General Assembly adopted the 2030 agenda for Sustainable Development that includes 17
It is artificially created efficient computing systems designed to simulate the human brain. It includes machine
Sustainable Development Goals (SDGs).
learning as a part of artificial intelligence. An ANN in its training phase is capable of learning by recognising
patterns in data which is later used to generate the desired output.
185
Introduction to AI
ANN is made up of three basic layers—Input, Hidden and Output. The input layer accepts the inputs, the hidden
Visit: https://next.rockpaperscissors.ai/ or scan the QR code to play the game.
Ice Breaker Activity: layer processes the inputs, and the output layer produces the result where each layer tries to learn from the
computed weights. It is the foundation of AI and is used to solve complex problems that are difficult for humans.
The challenge here is to win 20 games against AI before AI wins them against you. Answer It consists of hardware or software that operates just like neurons of the human brain. Commercial application
Video Session:
This section allows students to familiarise of ANN is in solving complex signal processing, predictions or pattern recognition problems.
the following questions after playing the game:
1. Did you manage to win? This section contains a link of the
with the concept with the help of an Biological Neural Network
video related to the topic for better
activity. It is composed of a group of chemically connected or functionally associated neurons. Neurons transmit electrical
signals to other neurons. These neurons are the building blocks of the complete central nervous system of the
living body. Brain is the control unit of this neural network.
understanding of the concept.
An understanding of the biological neural network has led to the development of the Artificial Neural Network
where these computing systems learn and adapt to the situations and inputs just like Biological Neural Network.
Experiential Learning
Video Session
154 Touchpad Artificial Intelligence (Ver. 2.0)-IX
Visit: https://experiments.withgoogle.com/what-neural-nets-see or scan the QR code.
This experiment lets you turn on your camera to explore what neural nets see, live,
using your camera. Watch the video explainer above to see how each layer of the neural
networks.
Neural Networks 259
AI Innovators:
AI Glossary: It presents information about the
This section contains pioneers in the field of AI.
definition of important AI terms.

