Scribd
Upload
109 views18 pages

Artificial Neural Networks

Artificial neural networks are models inspired by biological neural networks. They are composed of artificial neurons that are connected in layers. During training, the neural network learns by considering examples and receiving feedback to strengthen connections between neurons. Once trained, the network can perform tasks like classification and prediction. Neural networks have advantages like fault tolerance and the ability to learn without reprogramming. They are applied in areas like prediction, classification, data processing, and computer vision.

Uploaded by

Rajalaxmi Devagirkar Kangokar
Copyright
© Attribution Non-Commercial (BY-NC)
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
109 views18 pages

Artificial Neural Networks

Artificial neural networks are models inspired by biological neural networks. They are composed of artificial neurons that are connected in layers. During training, the neural network learns by considering examples and receiving feedback to strengthen connections between neurons. Once trained, the network can perform tasks like classification and prediction. Neural networks have advantages like fault tolerance and the ability to learn without reprogramming. They are applied in areas like prediction, classification, data processing, and computer vision.

Uploaded by

Rajalaxmi Devagirkar Kangokar
Copyright
© Attribution Non-Commercial (BY-NC)
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/ 18

ARTIFICIAL NEURAL

NETWORKS
Guided By:
Prof Veena.A.Patil

Presented By:
RAJALAXMI.R.D
INTRODUCTION
What is neural computing/neural
networks?

• Models of the brain and nervous system


Brain-Like Computer
• Highly parallel

• Very complex behaviours ?


•Artificial Neural network is a system loosely
modeled on the human brain.

•It is an attempt to simulate within specialized


hardware or sophisticated software.

•Artificial Neural networks can also be called as parallel

distributed processing, natural intelligent systems and


machine learning algorithms etc..
BIOLOGICAL NEURON

A typical neuron collects signals from other


neurons through a host of fine structures
called dendrites

The neuron sends out spikes of electrical


activity through a long, thin strand known as

an axon, which splits into thousands of


branches

At the end of the branch, a structure called a


synapse converts the activity from the axon
into electrical effects.
• A good example is the processing of
visual information:

A one-year-old baby is much better and faster


at recognising objects, faces, and other visual
features than even the most advanced AI
system running on the fastest super computer.
THE ARTIFICIAL NEURON

•An artificial neuron is a device with


many inputs and one output.
•The neuron has two modes of operation;
 The training mode.
 The using mode.
Training Mode:

• The task is similar to teaching a


student.

• First, we show him some examples.

• After that, we ask him to solve some


problems.

• Finally, we correct him, and start the


whole process again.

• Hopefully, he’ll get it right after a


couple of rounds…
User Mode:

• Network simulation = input signals flow through


network to outputs

• Output is often a binary decision

• Simple operations

Fast Decisions And Real-time Response


ARTIFICIAL NEURAL
NETWORK
• Arranging neurons in various layers.

• Deciding the type of connections among neurons for


different layers, as well as among the neurons within a
layer.

• Deciding the way a neuron receives input and produces


output.

• Determining the strength of connection within the


network of weights by using a training data set.
COMPONENTS NEEDED:
In order for a neural network to learn it needs 2 basic
components:
 Inputs
Which consists of any information the expert
uses to determine his/her final decision or
outcome.
 Outputs
Which are the decisions or outcome arrived at
by the expert that correspond to the inputs
entered.
TYPES OF CONNECTIONS
• Inter-layer • Intra-layer
Connections Connections.
o Fully connected
o Recurrent
o Feed forward
o On-center/off surround
o Bi-directional

o Hierarchical

o Resonance
ADVANTAGES
• A neural network can perform tasks that a linear
program can not.

• When an element of the neural network fails, it can


continue without any problem by their parallel nature.

• A neural network learns and does not need to be


reprogrammed.

• It can be implemented in any application without any


problem.
DISADVANTAGES
• The neural network needs training to operate.

• The architecture of a neural network is different from


the architecture of microprocessors therefore needs
to be emulated.

• Requires high processing time for large neural


networks.
AREAS OF APPLICATION
most applications of neural networks fall into the
following five categories:
•Prediction: Uses input values to predict some output.

• Classification: Uses input values to determine the classification.

• Data association: It recognizes the data that contains errors.

• Data-conceptualization: Analyze the inputs so that grouping


relationships can be inferred.

•Data filtering: Smoothes an input signal.


APPLICATIONS OF ANN
• Speech/Voice recognition

• Face detection/Recognition

• Pronunciation (NET talk)

• Navigation of a car

• Signal processing/Communication

• Imaging/Vision
conclusion
Neural Networks to offer unique solutions to
problems in different fields. the ability of neural
networks to learn allows them to be used on
problems where straightforward solutions do not
exist.
THANK YOU

You might also like