0% found this document useful (0 votes)
2K views14 pages

Machine Learning: in Telugu

This document provides an introduction to machine learning, including: 1. It discusses the history and definitions of machine learning, describing it as a subset of artificial intelligence that allows machines to learn from past data. 2. The main types of machine learning are described as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. 3. Popular applications of machine learning include facial recognition, speech recognition, financial services, marketing, healthcare, and recommendation systems.

Uploaded by

a balu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2K views14 pages

Machine Learning: in Telugu

This document provides an introduction to machine learning, including: 1. It discusses the history and definitions of machine learning, describing it as a subset of artificial intelligence that allows machines to learn from past data. 2. The main types of machine learning are described as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. 3. Popular applications of machine learning include facial recognition, speech recognition, financial services, marketing, healthcare, and recommendation systems.

Uploaded by

a balu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

Machine Learning

in Telugu

Chapter - 1
Introduction
• It was developed by Arthur Samual in the year
1959. He was a pioneer Arti icial Intelligence and
computer gaming and de ined machine learning
as “Field of study that gives computers the
capability to learn without being explicitly
programmed
f
f
• A Technology that enables a machine to stimulate human
behaviour to help in solving complex problems is known as
Arti icial Intelligence. Machine learning is a subset of Arti icial
Intelligence and allows machines to learn from past data and
provide an accurate output. Arti icial intelligence deals with
unstructured as well as structured data whereas machine
learning deals with structured and semistructured data
f
f
f
• The function of a machine learning system can be
descriptive meaning that the system used the data to
explain what happened predictive meaning the system
uses the data to predict what will happen or prescriptive
meaning the system will use the data to make
suggestions about what action to take.
Seven steps for Machine Learning

• Gathering data
• Preparing that data
• Choosing a model
• Training
• Evaluation
• Hyperparametre tunning
• Prediction
Types of Machine Learning

• Supervised Learning
• Unsupervised learning
• Semi supervised learning
• Reinforcement learning
Supervised Learning

• The Supervised learning model has a set of input variables, and an output variables.
An algorithm identi ies the mapping function between the input and output variables.
1. Regression— used to predict future values and the model is trained with
the historical data.
Ex: Predicting the future price of a product
2. Classi ication— various labels train the algorithm to identity items within a
speci ic category.
Ex: disease or no disease, apple or orange.
f
f
f
Unsupervised Learning
This approach is the one where the output is unknown and we have only the input variable at
hand. The algorithm learns by itself and discovers an impressive structure in the data.
We can group the unsupervised learning problem are :

1. Clustering: this means bundling the input variables, with the same
Characteristics together
Ex: grouping users based on search history
2. Association : Here we discover the rules that govern meaning fun association among
The data set
Ex: people who watch X and will also watch Y
Semi-supervised learning

• In this model with a minimal amount of labelled data and a


large amount of unlabelled data. Usually the irst step is to
cluster similar data with the help of an unsupervised machine
learning algorithm. The next step is to label the unlabelled
data using the characteristics of the limited labelled data
available. After labelling the complete data one van use
supervised learning algorithms to solve the problem

f
Reinforcement Learning

• In this approach machine learning models are trained to make a series of


decisions based on the rewards and feedback they receive for their
actions. The machine learns to achieve a goal in complex and uncertain
situations and is rewarded each time it achieves it during the learning
period. Reinforcement learning is di erent from supervised learning in the
sense that there is no answer available, so the reinforcement agent
decides the steps to perform a task. The machine learns from its own
experience when there is no training data set present.
ff
Applications of Machine Learning

• Facial recognition / image recognition


• Automatic speech recognition
• Financial services
• Marketing and sales
• Healthcare
• Recommendations systems
Facial recognition / image recognition

• The most common application of machine learning is facial recognition


and the simplest example of this application if the iPhone X
Automatic speech recognition

• Abbreviated as ASR, automatic speech recognition is used to


convert speech into digital text, its application lie in
authenticating users based on their voice and performing
tasks based on the human voice inputs
Financial Services

• Financial monitoring to detect money laundering activities


is also a critical security use case of machine learning.
Machine learning also helps in making better trading
decisions withe the help of algorithms that can analyse
thousands of data sources simultaneously. Credit scoring
and underwriting are some of the other applications.

You might also like