Scribd
Upload
13 views

Machine Learning

Machine learning is a method of developing computer systems that can learn from data without being explicitly programmed. There are three main types of machine learning: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled training data to learn relationships between inputs and outputs. Unsupervised learning discovers patterns in unlabeled data. Reinforcement learning involves an agent learning through trial-and-error interactions with an environment. Machine learning has applications across many fields and can automate tasks, make predictions, and improve over time with more data. However, it also faces challenges regarding data quality, bias, complexity, and other issues.

Uploaded by

Astrogen Astrogen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
13 views

Machine Learning

Machine learning is a method of developing computer systems that can learn from data without being explicitly programmed. There are three main types of machine learning: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled training data to learn relationships between inputs and outputs. Unsupervised learning discovers patterns in unlabeled data. Reinforcement learning involves an agent learning through trial-and-error interactions with an environment. Machine learning has applications across many fields and can automate tasks, make predictions, and improve over time with more data. However, it also faces challenges regarding data quality, bias, complexity, and other issues.

Uploaded by

Astrogen Astrogen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

MACHINE

LEARNING
Presented by: Simon Manandhar
Bsc.CSIT 1st Semester
Sec “A”
TABLE OF CONTENTS
01 05 Challenges of
Introduction
Machine Learning
02 Types of Machine 06 Application of
Learning Machine Learning
03 Working 07
Conclusion
Mechanism of ML

04 Why Machine
Learning
2
Introduction
⬢ Development of computer systems that are capable of
learning without being given explicit instructions by
analyzing data patterns using algorithms.

⬢ Computer-assisted method that allows computers to


solve issues with little or no human intervention and
take actions based on previous observations.[1]

⬢ Discover patterns in data and then make predictions


based on often finding answers to questions, detect
and analyze trends and help solve problems.

3
Supervised
Learning

Types of
Unsupervised
TYPES
Machine Learning
Learning

Reinforcement
Learning
4
Supervised Unsupervised Reinforcement
Learning Learning Learning

• Supervised learning: Model • Reinforcement learning agent


trained on labeled data with • Unsupervised learning: Model learns to make decisions by
known inputs and outputs. trained on unlabeled data where interacting with an
[2] only inputs are known. environment.[3]

• Goal: Learn a mapping from • Goal : Discover patterns • Goal: learn a policy that
input data to output labels without output knowledge maximizes the long-term reward
for accurate predictions on
new data.

5
Working Mechanism
Data
Data collection
processing

Model selection Feature


and training engineering

Evaluation and
Deployment
6
7
8

n
atio cy
tom ien on
Au effic ati
predictions

aliz
and
Accurate

son
Per
improvement
Continuous
g
kin a
n-m
isio d
dec rove n
Im
p
te ct i o
De
ud
Fra
Challenges of machine learning
⬢ Bias and fairness

⬢ Complexity

⬢ Data requirements

⬢ Overfitting[4]

⬢ Dependence on technology

9
APPLICATION
OF MACHINE
LEARNING

10
Conclusion
In conclusion, machine learning has revolutionized the way we
approach data analysis and decision-making. By enabling
algorithms to learn from data and make predictions or decisions
without being explicitly programmed, machine learning has
opened up new possibilities in fields ranging from healthcare to
finance to transportation.
However, machine learning also presents a number of
challenges, including data quality and quantity, interpretability,
overfitting, algorithm selection, computing power, bias and
fairness, and regulatory and ethical concerns. Addressing these
challenges requires a collaborative effort between data scientists,
domain experts, and policymakers.
11
References
[1] "javapoint.com," [Online]. Available: https://www.javatpoint.com/machine-
learning. [Accessed 05 04 2023].
[2] "elearninginductry," [Online]. Available:
https://elearningindustry.com/machine-learning-process-and-scenarios.
[Accessed 06 04 2023].
[3] "coursera.org," [Online]. Available: https://www.coursera.org/articles/types-
of-machine-learning. [Accessed 04 04 2023].
[4] "edureka.co," [Online]. Available: https://www.edureka.co/blog/machine-
learning-applications/. [Accessed 05 04 2023].
“
Thank you

13

You might also like