Unit 1 – Introduction to Machine Learning

• What is Machine Learning?, : “What is machine learning?” It’s a question that

opens the door to a new era of technology—one where computers can learn and
improve on their own, much like humans. Imagine a world where computers
don’t just follow strict rules but can learn from data and experiences. This is the
essence of machine learning.

Machine learning is an application of AI that includes algorithms that parse data,

learn from that data, and then apply what they’ve learned to make informed
decisions.
An easy example of a machine learning algorithm is an on-demand music
streaming service like Spotify.
For Spotify to make a decision about which new songs or artists to recommend to
you, machine learning algorithms associate your preferences with other listeners
who have a similar musical taste. This technique, which is often simply touted as
AI, is used in many services that offer automated recommendations.
Machine learning fuels all sorts of tasks that span across multiple industries, from
data security firms that hunt down malware to finance professionals who want
alerts for favorable trades. The AI algorithms are programmed to constantly be
learning in a way that simulates as a virtual personal assistant—something that
they do quite well.

• History of Machine Learning:

In the 1990s work on machine learning shifted from a knowledge-driven approach
to a data-driven approach. Scientists began creating programs for computers to
analyze large amounts of data and draw conclusions — or “learn” — from the
results.
And in 1997, IBM’s Deep Blue shocked the world by beating the world champion
at chess.

The term “deep learning” was coined in 2006 by Geoffrey Hinton to explain new
algorithms that let computers “see” and distinguish objects and text in images and
videos.

Four years later, in 2010 Microsoft revealed their Kinect technology could track 20
human features at a rate of 30 times per second, allowing people to interact with
the computer via movements and gestures. The follow year IBM’s Watson beat its
human competitors at Jeopardy.

Google Brain was developed in 2011 and its deep neural network could learn to
discover and categorize objects much the way a cat does. The following year, the
tech giant’s X Lab developed a machine learning algorithm that is able to
autonomously browse YouTube videos to identify the videos that contain cats.

In 2014, Facebook developed DeepFace, a software algorithm that is able to

recognize or verify individuals on photos to the same level as humans can.
2015 - Present day

Amazon launched its own machine learning platform in 2015. Microsoft also
created the Distributed Machine Learning Toolkit, which enabled the efficient
distribution of machine learning problems across multiple computers.

Then more 3,000 AI and Robotics researchers, endorsed by Stephen

Hawking, Elon Musk and Steve Wozniak (among many others), signed an open
letter warning of the danger of autonomous weapons which select and engage
targets without human intervention.

In 2016 Google’s artificial intelligence algorithm beat a professional player at the

Chinese board game Go, which is considered the world’s most complex board
game and is many times harder than chess.

The AlphaGo algorithm developed by Google DeepMind managed to win five

games out of five in the Go competition.

Waymo started testing autonomous cars in the US in 2017 with backup drivers
only at the back of the car. Later the same year they introduce completely
autonomous taxis in the city of Phoenix.

In 2020, while the rest of the world was in the grips of the pandemic, open AI
announced a ground-breaking natural language processing algorithm GPT-3 with a
remarkable ability to generate human-like text when given a prompt.

Today, GPT-3 is considered the largest and most advanced language model in the
world, using 175 billion parameters and Microsoft Azure’s AI supercomputer for
training.
• Need of Machine Learning:

Finding ways to make work easier is what drives people to invent (better)
machines. Machines allow us to do many things quicker or with less effort. They
also enable us to do things that we otherwise would not be able to do.

• Features of Machine learning:

 Machine learning is data driven technology. Large amount of data generated

by organizations on daily bases. So, by notable relationships in data,
organizations makes better decisions.
 Machine can learn itself from past data and automatically improve.
 From the given dataset it detects various patterns on data.
 For the big organizations branding is important and it will become more easy
to target relatable customer base.
 It is similar to data mining because it is also deals with the huge amount of
data.
• Applications of Machine learning:

1. Image Recognition:

Image recognition is one of the most common applications of machine learning. It

is used to identify objects, persons, places, digital images, etc. The popular use
case of image recognition and face detection is, Automatic friend tagging
suggestion:

Facebook provides us a feature of auto friend tagging suggestion. Whenever we

upload a photo with our Facebook friends, then we automatically get a tagging
suggestion with name, and the technology behind this is machine learning's face
detection and recognition algorithm.
It is based on the Facebook project named "Deep Face," which is responsible for
face recognition and person identification in the picture.

2. Speech Recognition

While using Google, we get an option of "Search by voice," it comes under speech
recognition, and it's a popular application of machine learning.

Speech recognition is a process of converting voice instructions into text, and it is

also known as "Speech to text", or "Computer speech recognition." At present,
machine learning algorithms are widely used by various applications of speech
recognition. Google assistant, Siri, Cortana, and Alexa are using speech
recognition technology to follow the voice instructions.

3. Traffic prediction:

If we want to visit a new place, we take help of Google Maps, which shows us the
correct path with the shortest route and predicts the traffic conditions.

It predicts the traffic conditions such as whether traffic is cleared, slow-moving, or

heavily congested with the help of two ways:

ADVERTISEMENT

o Real Time location of the vehicle form Google Map app and sensors
o Average time has taken on past days at the same time.

Everyone who is using Google Map is helping this app to make it better. It takes
information from the user and sends back to its database to improve the
performance.

4. Product recommendations:

Machine learning is widely used by various e-commerce and entertainment

companies such as Amazon, Netflix, etc., for product recommendation to the user.
Whenever we search for some product on Amazon, then we started getting an
advertisement for the same product while internet surfing on the same browser and
this is because of machine learning.

Google understands the user interest using various machine learning algorithms
and suggests the product as per customer interest.
As similar, when we use Netflix, we find some recommendations for entertainment
series, movies, etc., and this is also done with the help of machine learning.

5. Self-driving cars:

One of the most exciting applications of machine learning is self-driving cars.

Machine learning plays a significant role in self-driving cars. Tesla, the most
popular car manufacturing company is working on self-driving car. It is using
unsupervised learning method to train the car models to detect people and objects
while driving.

6. Email Spam and Malware Filtering:

Whenever we receive a new email, it is filtered automatically as important, normal,

and spam. We always receive an important mail in our inbox with the important
symbol and spam emails in our spam box, and the technology behind this is
Machine learning. Below are some spam filters used by Gmail:

o Content Filter
o Header filter
o General blacklists filter
o Rules-based filters
o Permission filters

Some machine learning algorithms such as Multi-Layer Perceptron, Decision

tree, and Naïve Bayes classifier are used for email spam filtering and malware
detection.

7. Virtual Personal Assistant:

We have various virtual personal assistants such as Google

assistant, Alexa, Cortana, Siri. As the name suggests, they help us in finding the
information using our voice instruction. These assistants can help us in various
ways just by our voice instructions such as Play music, call someone, Open an
email, Scheduling an appointment, etc.

These virtual assistants use machine learning algorithms as an important part.

These assistant record our voice instructions, send it over the server on a cloud,
and decode it using ML algorithms and act accordingly.

8. Online Fraud Detection:

Machine learning is making our online transaction safe and secure by detecting
fraud transaction. Whenever we perform some online transaction, there may be
various ways that a fraudulent transaction can take place such as fake
accounts, fake ids, and steal money in the middle of a transaction. So to detect
this, Feed Forward Neural network helps us by checking whether it is a genuine
transaction or a fraud transaction.

For each genuine transaction, the output is converted into some hash values, and
these values become the input for the next round. For each genuine transaction,
there is a specific pattern which gets change for the fraud transaction hence, it
detects it and makes our online transactions more secure.

9. Stock Market trading:

Machine learning is widely used in stock market trading. In the stock market, there
is always a risk of up and downs in shares, so for this machine learning's long
short term memory neural network is used for the prediction of stock market
trends.

10. Medical Diagnosis:

In medical science, machine learning is used for diseases diagnoses. With this,
medical technology is growing very fast and able to build 3D models that can
predict the exact position of lesions in the brain.

It helps in finding brain tumors and other brain-related diseases easily.

11. Automatic Language Translation:

Nowadays, if we visit a new place and we are not aware of the language then it is
not a problem at all, as for this also machine learning helps us by converting the
text into our known languages. Google's GNMT (Google Neural Machine
Translation) provide this feature, which is a Neural Machine Learning that
translates the text into our familiar language, and it called as automatic translation.
The technology behind the automatic translation is a sequence to sequence learning
algorithm, which is used with image recognition and translates the text from one
language to another language.

• Types of Machine Learning:

There are several types of machine learning, each with special characteristics and
applications. Some of the main types of machine learning algorithms are as
follows:
1. Supervised Machine Learning
2. Unsupervised Machine Learning
3. Semi-Supervised Machine Learning
4. Reinforcement Learning

1. Supervised Machine Learning

Supervised learning is defined as when a model gets trained on a “Labelled
Dataset”. Labelled datasets have both input and output parameters.
In Supervised Learning algorithms learn to map points between inputs and
correct outputs. It has both training and validation datasets labelled.

Supervised Learning
Let’s understand it with the help of an example.
Example: Consider a scenario where you have to build an image classifier to
differentiate between cats and dogs. If you feed the datasets of dogs and cats
labelled images to the algorithm, the machine will learn to classify between a dog
or a cat from these labeled images. When we input new dog or cat images that it
has never seen before, it will use the learned algorithms and predict whether it is
a dog or a cat. This is how supervised learning works, and this is particularly an
image classification.
There are two main categories of supervised learning that are mentioned below:
2. Unsupervised Machine Learning
Unsupervised Learning Unsupervised learning is a type of machine learning
technique in which an algorithm discovers patterns and relationships
using unlabeled data. Unlike supervised learning, unsupervised learning doesn’t
involve providing the algorithm with labeled target outputs. The primary goal of
Unsupervised learning is often to discover hidden patterns, similarities, or
clusters within the data, which can then be used for various purposes, such as data
exploration, visualization, dimensionality reduction, and more.

Unsupervised Learning

Let’s understand it with the help of an example.

Example: Consider that you have a dataset that contains information about the
purchases you made from the shop. Through clustering, the algorithm can group
the same purchasing behavior among you and other customers, which reveals
potential customers without predefined labels. This type of information can help
businesses get target customers as well as identify outliers.
3. Semi-Supervised Learning
Semi-Supervised learning is a machine learning algorithm that works between
the supervised and unsupervised learning so it uses both labelled and
unlabelled data. It’s particularly useful when obtaining labeled data is costly,
time-consuming, or resource-intensive. This approach is useful when the dataset
is expensive and time-consuming. Semi-supervised learning is chosen when
labeled data requires skills and relevant resources in order to train or learn from
it.
We use these techniques when we are dealing with data that is a little bit labeled
and the rest large portion of it is unlabeled. We can use the unsupervised
techniques to predict labels and then feed these labels to supervised techniques.
This technique is mostly applicable in the case of image data sets where usually
all images are not labeled.

Semi-Supervised Learning

Let’s understand it with the help of an example.

Example: Consider that we are building a language translation model, having
labeled translations for every sentence pair can be resources intensive. It allows
the models to learn from labeled and unlabeled sentence pairs, making them more
accurate. This technique has led to significant improvements in the quality of
machine translation services.
4. Reinforcement Machine Learning
Reinforcement machine learning algorithm is a learning method that interacts
with the environment by producing actions and discovering errors. Trial, error,
and delay are the most relevant characteristics of reinforcement learning. In this
technique, the model keeps on increasing its performance using Reward Feedback
to learn the behavior or pattern. These algorithms are specific to a particular
problem e.g. Google Self Driving car, AlphaGo where a bot competes with
humans and even itself to get better and better performers in Go Game. Each time
we feed in data, they learn and add the data to their knowledge which is training
data. So, the more it learns the better it gets trained and hence experienced.
Here are some of most common reinforcement learning algorithms:
 Q-learning: Q-learning is a model-free RL algorithm that learns a Q-function,
which maps states to actions. The Q-function estimates the expected reward of
taking a particular action in a given state.
 SARSA (State-Action-Reward-State-Action): SARSA is another model-free
RL algorithm that learns a Q-function. However, unlike Q-learning, SARSA
updates the Q-function for the action that was actually taken, rather than the
optimal action.
 Deep Q-learning: Deep Q-learning is a combination of Q-learning and deep
learning. Deep Q-learning uses a neural network to represent the Q-function,
which allows it to learn complex relationships between states and actions.

Reinforcement Machine Learning

Let’s understand it with the help of examples.
Example: Consider that you are training an AI agent to play a game like chess.
The agent explores different moves and receives positive or negative feedback
based on the outcome. Reinforcement Learning also finds applications in which
they learn to perform tasks by interacting with their surroundings.

• Examples of Machine Learning:

1. Speech & Image Recognition

Computer Speech Recognition or Automatic Speech Recognition helps to convert

speech into text. Many applications convert the live speech into an audio file
format and later convert it into a text file.

Voice search, voice dialing, and appliance control are some real-world examples
of speech recognition. Alexa and Google Home are the most widely used speech
recognition software.

Similar to speech recognition, Image recognition is also the most widely used
example of Machine Learning technology that helps identify any object in the form
of a digital image. There are some real-world examples of Image recognition, such
as,

Further, there is the biggest example of Image recognition is facial recognition.

We all are using new generation mobile phones, where we use facial recognition
techniques to unlock our devices. Hence, it also helps to increase the security of
the system.

2. Traffic alerts using Google Map

Google Map is one of the widely used applications whenever anyone goes out to
reach the correct destination. The map helps us find the best route or fastest route,
traffic, and much more information. But how it provides this information to us?

Google map uses different technologies, including machine learning

which collects information from different users, analyze that information, update
the information, and make predictions. With the help of predictions, it can also tell
us the traffic before we start our journey.
Machine Learning also helps identify the best and fastest route while we are in
traffic using Google Maps. Further, we can also answer some questions like does
the route still have traffic? This information and data get stored automatically in
the database, which Machine Learning uses for the exact information for other
people in traffic. Further, Google maps also help find locations like a hotel, mall,
restaurant, cinema hall, buses, etc.

3. Chatbot (Online Customer Support)

A chatbot is the most widely used software in every industry like banking,
Medical, education, health, etc. You can see chatbots in any banking application
for quick online support to customers.

These chatbots also work on the concepts of Machine Learning. The programmers
feed some basic questions and answers based on the frequently asked queries. So,
whenever a customer asks a query, the chatbot recognizes the question's keywords
from a database and then provides appropriate resolution to the customer. This
helps to make quick and fast customer service facilities to customers.

4. Google Translation

Suppose you work on an international banking project like French, German, etc.,
but you only know English. In that case, this will be a very panic moment for you
because you can't proceed further without reviewing documents. Google Translator
software helps to translate any language into the desired language. So, in this way,
you can convert French, German, etc., into English, Hindi, or any other language.
This makes the job of different sectors very easy as a user can work on any
country's project hassle-free.

Google uses the Google Neural Machine Translation to detect any language and
translate it into any desired language.

5. Prediction

Prediction system also uses Machine learning algorithms for making predictions.
There are various sectors where predictions are used. For example, in bank loan
systems, error probability can be determined using predictions with machine
learning. For this, the available data are classified into different groups with the set
of rules provided by analysts, and once the classification is done, the error
probability is predicted.
6. Extraction

One of the best examples of machine learning is the extraction of information. In

this process, structured data is extracted from unstructured data, and which is used
in predictive analytics tools. The data is usually found in a raw or unstructured
form that is not useful, and to make it useful, the extraction process is used. Some
real-world examples of extraction are:

ADVERTISEMENT

o Generating a model to predict vocal cord disorders.

o Helping diagnosis and treatment of problem faster.

7. Statistical Arbitrage

Arbitrage is an automated trading process, which is used in the finance industry to

manage a large volume of securities. The process uses a trading algorithm to
analyze a set of securities using economic variables and correlations. Some
examples of statistical arbitrage are as follows:

o Algorithmic trading that analyses a market microstructure

o Analyze large data sets
o Identify real-time arbitrage opportunities
o Machine learning optimizes the arbitrage strategy to enhance results.

8. Auto-Friend Tagging Suggestion

One of the popular examples of machine learning is the Auto-friend tagging

suggestions feature by Facebook. Whenever we upload a new picture on Facebook
with friends, it suggests to tag the friends and automatically provides the names.
Facebook does it by using DeepFace, which is a facial recognition system created
by Facebook. It identifies the faces and images also.

9. Self-driving cars

The future of the automobile industry is self-driving cars. These are driverless cars,
which are based on concepts of deep learning and machine learning. Some
commonly used machine learning algorithms in self-driving cars are Scale-
invariant feature transform (SIFT), AdaBoost, TextonBoost, YOLO(You only look
once).

10. Ads Recommendation

Nowadays, most people spend multiple hours on google or the internet surfing.
And while working on any webpage or website, they get multiples ads on each
page. But these ads are different for each user even when two users are using the
same internet and on the same location. These ads recommendations are done with
the help of machine learning algorithms. These ads recommendations are based on
the search history of each user. For example, if one user searches for the Shirt on
Amazon or any other e-commerce website, he will get start ads recommendation of
shirts after some time.

11. Video Surveillance

Video Surveillance is an advanced application of AI and machine learning, which

can detect any crime before it happens. It is much efficient than observed by a
human because it is a much difficult and boring task for a human to keep
monitoring multiple videos; that's why machines are the better option. Video
surveillance is very useful as they keep looking for specific behavior of people like
standing motionless for a long time, stumbling, or napping on benches, etc.
Whenever the surveillance system finds any unusual activity, it alerts the
respective team, which can stop or help avoid some mishappening at that place.

Some popular uses of video surveillance are:

o Facility protections
o Operation monitoring
o Parking lots
o Traffic monitoring
o Shopping patterns

12. Email & spam filtering

Emails are filtered automatically when we receive any new email, and it is also an
example of machine learning. We always receive an important mail in our inbox
with the important symbol and spam emails in our spam box, and the technology
behind this is Machine learning. Below are some spam filters used by Gmail:
 o Content Filter
o Header filter
o General blacklists filter
o Rules-based filters
o Permission filters

Some machine learning algorithms that are used in email spam filtering and
malware detection are Multi-Layer Perceptron, Decision tree, and Naïve Bayes
classifier.

13. Real-Time Dynamic Pricing

Whenever we book an Uber in peak office hours in the morning or evening, we get
a difference in prices compared to normal hours. The prices are hiked due to surge
prices applied by companies whenever demand is high. But how these surge prices
are determined & applied by companies. So, the technologies behind this are AI
and machine learning. These technologies solve two main business queries, which
are

o The reaction of customers on surge prices

o Suggesting optimum prices so that no harm of customer losing occurs to
business.

Machine Learning technology also helps in finding discounted prices, best

prices, promotional prices, etc., for each customer.

14. Gaming and Education

Machine learning technology is widely being used in gaming and education. There
are various gaming and learning apps that are using AI and Machine learning.
Among these apps, Duolingo is a free language learning app, which is designed in
a fun and interactive way. While using this app, people feel like playing a game on
the phone.

It collects data from the user's answer and creates a statical model to determine that
how long a person can remember the word, and before requiring a refresher, it
provides that information.
15. Virtual Assistants

Virtual assistants are much popular in today's world, which are the smart software
embedded in smartphones or laptops. These assistants work as personal assistants
and assist in searching for information that is asked over voice. A virtual assistant
understands human language or natural language voice commands and performs
the task for that user. Some examples of virtual assistants are Siri, Alexa, Google,
Cortana, etc. To start working with these virtual assistants, first, they need to be
activated, and then we can ask anything, and they will answer it. For example,
"What's the date today?", "Tell me a joke", and many more. The technologies used
behind Virtual assistants are AI, machine learning, natural language processing,
etc. Machine learning algorithms collect and analyze the data based on the
previous involvement of the user and predict data as per the user preferences.