You are on page 1of 15

Pimpri Chinchwad Education Trust’s

Pimpri Chinchwad College of Engineering & Research


Department of Mechanical Engineering
Academic Year : 2021-22 (Semester-II)
Presentation on topic: Supervised, unsupervised and reinforcement learning approach.
Presented By
Rushikesh Gajanan Pote
SE Mechanical : Div. - __B____., Roll No. - __TE-B-16__)

Under the subject of

Artificial Intelligence &Machine Learning


Expt.-1 : To study supervised, unsupervised and reinforcement Learning approach.
Content

• What Is Machine Learning


• Supervised Learning
• Unsupervised Learning
• Reinforcement Learning
What Is Machine learning??

• Machine learning is a branch of artificial intelligence (AI) and computer


science which focuses on the use of data and algorithms to imitate the
way that humans learn, gradually improving its accuracy.
Supervised learning
•supervised learning -It is defined by its use of labeled datasets to train
algorithms that to classify data or predict outcomes accurately.his
training dataset includes inputs and correct outputs, which allow the
model to learn over time.

Types
• Classification- uses an algorithm to accurately assign test data into
specific categories
• Regression- is used to understand the relationship between
dependent and independent variables
• Advantages

-Supervised learning in Machine Learning allows you to collect data or produce a data output
from the previous experience.
Helps you to optimize performance criteria using experience.
Supervised machine learning helps you to solve various types of real-world computation
problems.

Disadvantages
-Computation time is high.
Real life example
Unsupervised learning a

un supervised learning, the main idea is to learn under supervision, where the
supervision signal is named as target value or label. In unsupervised learning,
we lack this kind of signal. Therefore, we need to find our way without any
supervision or guidance.

we don't go in dark there is reference system


 Advantage  Disadvantages
• No previous knowledge of the • The spectral classes do not
image area is required. necessarily represent the
• The opportunity for human features on the ground.
error is minimized. • It does not consider spatial
• It produces unique spectral relationships in the data.
classes. • It can take time to interpret
• Relatively easy and fast to carry the spectral classes.
out.
Classification vs
clustering

❑ Classification and Clustering are the two types of learning


methods which characterize objects into groups by one or more
features. •Key Differences Between
Classification and Clustering
BASIS FOR 1.Classification is the process of classifying
COMPARISO CLASSIFICATION CLUSTERING the data with the help of class labels. On the
N other hand, Clustering is similar to
classification but there are no predefined
Basic This model This function maps the class labels.
function classifies data into one of the
the data into one multiple clusters where
of numerous the arrangement of data 1.Classification is geared with supervised
already defined items is relies on the learning. As against, clustering is also
definite classes. similarities between them. known as unsupervised learning.
Involved in Supervised Unsupervised learning
learning 1.Training sample is provided in
Training Labeled data Unlabelled data provided. classification method while in case of
sample is provided. clustering training data is not provided.
Real Life Example
Reinforcement learning
Reinforcement learning is an area of Machine Learning. It is about taking
suitable action to maximize reward in a particular situation. It is employed
by various software and machines to find the best possible behavior or
path it should take in a specific situation

Reinforcement learning differs from supervised learning in a way that in


supervised learning the training data has the answer key with it so the
model is trained with the correct answer itself whereas in reinforcement
learning, there is no answer but the reinforcement agent decides what to
do to perform the given task.

in the absence of trained data set it is used.


Real Life Example
 Advantages  Disadvantages
• Reinforcement Learning is used • Too much reinforcement
to solve complex problems that learning can lead to an overload
cannot be solved by conventional of states which can diminish the
techniques. results.
• This technique is preferred to • This algorithm is not preferable
achieve long-term results which for solving simple problems.
are very difficult to achieve. • This algorithm needs a lot of data
• This learning model is very similar and a lot of computation.
to the learning of human beings. • The curse of dimensionality limits
Hence, it is close to achieving reinforcement learning for real
perfection physical system
Thank you

You might also like