UNIT-1

Introduction:
 A subset of artificial intelligence known as machine learning focuses primarily on the
creation of algorithms that enable a computer to independently learn from data and
previous experiences.
 Arthur Samuel first used the term "machine learning" in 1959.
 It could be summarized as follows:
 Without being explicitly programmed, machine learning enables a machine to
automatically learn from data, improve performance from experiences, and predict
things.
 Machine learning algorithms create a mathematical model that, without being explicitly
programmed, aids in making predictions or decisions with the assistance of sample
historical data, or training data.
 For the purpose of developing predictive models, machine learning brings together
statistics and computer science.
 Algorithms that learn from historical data are either constructed or utilized in machine
learning.
 The performance will rise in proportion to the quantity of information we provide.
How does Machine Learning work:
 A machine learning system builds prediction models, learns from previous data, and
predicts the output of new data whenever it receives it.
 The amount of data helps to build a better model that accurately predicts the output,
which in turn affects the accuracy of the predicted output.
Features of Machine Learning:
 Machine learning uses data to detect various patterns in a given dataset.
 It can learn from past data and improve automatically.
 It is a data-driven technology.
 Machine learning is much similar to data mining as it also deals with the huge amount of
the Data.
What is Machine Learning?
 Machine Learning is defined as a technology that is used to train machines to perform
various actions such as predictions, recommendations, estimations, etc., based on
historical data or past experience.
 Machine Learning enables computers to behave like human beings by training them with
the help of past experience and predicted data.
 There are three key aspects of Machine Learning, which are as follows:
Task: A task is defined as the main problem in which we are interested. This task/problem can
be related to the predictions and recommendations and estimations, etc.
Experience: It is defined as learning from historical or past data and used to estimate and resolve
future tasks.
Performance: It is defined as the capacity of any machine to resolve any machine learning task
or problem and provide the best outcome for the same. However, performance is dependent on
the type of machine learning problems.
Techniques in Machine Learning
Machine Learning techniques are divided mainly into the following 4 categories:
1. Supervised Learning
  Supervised learning is applicable when a machine has sample data, i.e., input as well as
output data with correct labels. Correct labels are used to check the correctness of the
model using some labels and tags.
 Supervised learning technique helps us to predict future events with the help of past
experience and labeled examples. Initially, it analyses the known training dataset, and
later it introduces an inferred function that makes predictions about output values.
 Further, it also predicts errors during this entire learning process and also corrects those
errors through algorithms.
 Example: Let's assume we have a set of images tagged as ''dog''. A machine learning
algorithm is trained with these dog images so it can easily distinguish whether an image
is a dog or not.
2. Unsupervised Learning
 In unsupervised learning, a machine is trained with some input samples or labels only,
while output is not known.
 The training information is neither classified nor labeled; hence, a machine may not
always provide correct output compared to supervised learning.
 Although Unsupervised learning is less common in practical business settings, it helps in
exploring the data and can draw inferences from datasets to describe hidden structures
from unlabeled data.
 Example: Let's assume a machine is trained with some set of documents having different
categories (Type A, B, and C), and we have to organize them into appropriate groups.
Because the machine is provided only with input samples or without output, so, it can
organize these datasets into type A, type B, and type C categories, but it is not necessary
whether it is organized correctly or not.
3. Reinforcement Learning
 Reinforcement Learning is a feedback-based machine learning technique.
 In such type of learning, agents (computer programs) need to explore the environment,
perform actions, and on the basis of their actions, they get rewards as feedback.
 For each good action, they get a positive reward, and for each bad action, they get a
negative reward.
 The goal of a Reinforcement learning agent is to maximize the positive rewards.
 Since there is no labeled data, the agent is bound to learn by its experience only.
4. Semi-supervised Learning
 Semi-supervised Learning is an intermediate technique of both supervised and
unsupervised learning.
 It performs actions on datasets having few labels as well as unlabeled data. However, it
generally contains unlabeled data.
 Hence, it also reduces the cost of the machine learning model as labels are costly, but for
corporate purposes, it may have few labels.
 Further, it also increases the accuracy and performance of the machine learning model.
 Sem-supervised learning helps data scientists to overcome the drawback of supervised
and unsupervised learning.
 Speech analysis, web content classification, protein sequence classification, text
documents classifiers. etc., are some important applications of Semi-supervised learning.
Applications of Machine Learning
 Machine Learning is widely being used in approximately every sector, including healthcare,
marketing, finance, infrastructure, automation, etc.
 There are some important real-world examples of machine learning, which are as follows:
 Healthcare and Medical Diagnosis:
1. Machine Learning is used in healthcare industries that help in generating neural
networks.
2. These self-learning neural networks help specialists for providing quality treatment
by analyzing external data on a patient's condition, X-rays, CT scans, various tests,
and screenings. Other than treatment, machine learning is also helpful for cases like
automatic billing, clinical decision supports, and development of clinical care
guidelines, etc.
 Marketing:
1. Machine learning helps marketers to create various hypotheses, testing, evaluation, and
analyze datasets.
2. It helps us to quickly make predictions based on the concept of big data.
3. It is also helpful for stock marketing as most of the trading is done through bots and
based on calculations from machine learning algorithms.
4. Various Deep Learning Neural network helps to build trading models such as
Convolutional Neural Network, Recurrent Neural Network, Long-short term memory,
etc.
 Self-driving cars:
1. This is one of the most exciting applications of machine learning in today's world.
2. It plays a vital role in developing self-driving cars. Various automobile companies like
Tesla, Tata, etc., are continuously working for the development of self-driving cars.
3. It also becomes possible by the machine learning method (supervised learning), in which
a machine is trained to detect people and objects while driving.
 Speech Recognition:
1. Speech Recognition is one of the most popular applications of machine learning.
2. Nowadays, almost every mobile application comes with a voice search facility. This
''Search By Voice'' facility is also a part of speech recognition.
3. In this method, voice instructions are converted into text, which is known as Speech to
text" or "Computer speech recognition.
4. Google assistant, SIRI, Alexa, Cortana, etc., are some famous applications of speech
recognition.
 Traffic Prediction:
1. Machine Learning also helps us to find the shortest route to reach our destination by
using Google Maps.
2. It also helps us in predicting traffic conditions, whether it is cleared or congested,
through the real-time location of the Google Maps app and sensor.
 Image Recognition:
1. Image recognition is also an important application of machine learning for identifying
objects, persons, places, etc.
2. Face detection and auto friend tagging suggestion is the most famous application of
image recognition used by Facebook, Instagram, etc.
3. Whenever we upload photos with our Facebook friends, it automatically suggests their
names through image recognition technology.
 Product Recommendations:
1. Machine Learning is widely used in business industries for the marketing of various
products.
2. Almost all big and small companies like Amazon, Alibaba, Walmart, Netflix, etc., are
using machine learning techniques for products recommendation to their users.
3. Whenever we search for any products on their websites, we automatically get started with
lots of advertisements for similar products.
4. This is also possible by Machine Learning algorithms that learn users' interests and,
based on past data, suggest products to the user.
 Automatic Translation:
1. Automatic language translation is also one of the most significant applications of
machine learning that is based on sequence algorithms by translating text of one language
into other desirable languages.
2. Google GNMT (Google Neural Machine Translation) provides this feature, which is
Neural Machine Learning.
3. Further, you can also translate the selected text on images as well as complete documents
through Google Lens.
 Virtual Assistant:
1. A virtual personal assistant is also one of the most popular applications of machine
learning.
2. First, it records out voice and sends to cloud-based server then decodes it with the help of
machine learning algorithms.
3. All big companies like Amazon, Google, etc., are using these features for playing music,
calling someone, opening an app and searching data on the internet, etc.
 Email Spam and Malware Filtering:
1. Machine Learning also helps us to filter various Emails received on our mailbox
according to their category, such as important, normal, and spam.
2. It is possible by ML algorithms such as Multi-Layer Perceptron, Decision tree, and Naïve
Bayes classifier.
Towards Intelligent Machines Well Posed Problems: