Scribd
Upload
4 views10 pages

ANN3

The document discusses three types of learning in artificial neural networks: supervised, unsupervised, and reinforcement learning. Supervised learning involves training with existing data to predict outcomes, unsupervised learning groups data without guidance, and reinforcement learning optimizes actions based on feedback from the environment. Each learning type has distinct processes and applications in machine learning.

Uploaded by

sklahiri70
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
4 views10 pages

ANN3

The document discusses three types of learning in artificial neural networks: supervised, unsupervised, and reinforcement learning. Supervised learning involves training with existing data to predict outcomes, unsupervised learning groups data without guidance, and reinforcement learning optimizes actions based on feedback from the environment. Each learning type has distinct processes and applications in machine learning.

Uploaded by

sklahiri70
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/ 10

Understandin

g ANN
Learning
Type of learning

Supervised Unsupervise Reinforceme


learning d learning nt learning
Supervised learning

Supervised learning consists of two words supervised and


learning

Supervise intends to guide

We have supervisors whose duty is to guide and show the


way

We can see a similar case in the case of learning


Supervised learning

We have a data set,


Here the machine or and we assume the It implies the existing
program is learning results of new data data sets acts as a
with the help of the relying upon the supervisor or boss to
existing data set behavior of the find the new data
existing data sets

The price of
A basic example electronic gadgets is
being electronic predicted depending
gadgets price on what is observed
prediction with the prices of
other digital gadgets
Supervised learning

During the training of ANN under supervised learning,


the input vector is given to the network, which offers an
output vector

Afterward, the output vector is compared with the


desired output vector

An error signal is produced if there is a difference


between the actual output and the desired output
vector

Based on this error signal, the weight is adjusted until


the actual output is matched with the desired output
Unsupervised learning

As the name suggests, unsupervised learning refers to predict


something without any supervision or help from existing data

In this learning, the program learns by dividing the data with similar
characteristics into similar groups

In supervised learning, the data are grouped, relying upon similar


characteristics

In this situation, there are no existing data to look for direction

In other words, there is no supervisor


Unsupervised learning

During the training of the At the point when a new input


artificial neural network under pattern is implemented, then
unsupervised learning, the the neural network gives an
input vectors of a comparative output response showing the
type are joined to form class to which the input
clusters pattern belongs

Consequently, in this type of


There is no feedback from the
learning, the network itself
environment about what
must find the patterns and
should be the ideal output and
features from the input data
if it is either correct or
and the connection for the
incorrect
input data over the output
Reinforceme Reinforcement Learning is a
nt learning technique that helps to solve control
optimization issues

By using control optimization, we can


recognize the best action in each
state visited by the system in order
to optimize some objective function

Typically, reinforcement learning


comes into existence when the
system has a huge number of states
and has a complex stochastic
structure, which is not responsible to
closed-form analysis
Reinforcement learning

If issues have a
relatively small As the name suggests,
number of states, then this kind of learning is This learning
the random structure used to strengthen the procedure is like
is relatively simple, so network over some supervised learning
that one can utilize analyst data
dynamic programming

However, we may
have very little
information
Reinforcement learning

In reinforcement The feedback acquired


learning, during the here is evaluative, not
training of the This makes it fairly like instructive, which
network, the network supervised learning implies there is no
gets some feedback instructor as in
from the system supervised learning

After getting the


feedback, the
networks perform
modifications of the
weights to get better
Analyst data in the
future

You might also like