This presentation discussed about neural networks.History of neural networks.Working of both artificial and biological neurons.its connection types and also merits and demerits
2. CONTENTS
• Introduction
• History of Neural networks
• Working of Biological neuron
• Working of Artificial neuron
• Connection types
• Topologies
• Learning methods of neurons
• Applications
• Merits
• De-merits
• Conclusion
3. INTRODUCTION
• An Artificial Neural Network is an information processing paradigm
that is inspired by the way biological nervous systems, such as the
brain, process information.
• ANN is composed of a large number of highly interconnected
processing elements (neurons) working in unison to solve specific
problems.
• ANNs, like people, learn by example. An ANN is configured for a
specific application, such as pattern recognition or data
classification, through a learning process.
4. HISTORY OF NEURAL NETWORKS
• The history of neural networks begins before the invention
computer .i.e., in 1943.
• The first neural network construction is done by neurologists for
understanding the working of neurons.
• Later technologists are also interested in this networks.
• In recent years, the importance of neural networks was observed.
5. WORKING OF BIOLOGICAL
NEURON
• A biological neuron contains mainly four parts. They are:
• dendrites
• cell body
• axon and
• synapse.
6. •
WORKING OF ARTIFICIAL
NEURON
• An artificial neuron also contains dendrites,
Cell body, axon and synapse.
• In artificial neural networks, the inputs are taken only
when threshold value is satisfied. Otherwise inputs are not
taken by the neuron.
• There are two modes of neurons such as, training mode
and using mode.
7. CONNECTION TYPES IN NEURAL
NETWORKS
• Neurons are interconnected with each other,
for the transferring the data.
• There are two types of hierarchies for
connecting the neurons.
1. Static connection
2. Dynamic connection
8. 1. STATIC (FEED FORWARD):
• The feed forward neural network was the first and most
simple type of artificial neural network.
• In this network, the information will moves in one
direction only.
9. 2.DYNAMIC (FEED BACKWARD):
• Feed backward is advanced than feed forward.
• In feed backward, looping mechanism is
introduced.
10. TOPOLIGIES IN NEURAL NETWORK
• Topology defines how a neuron in neural network connected with
another neurons.
• There are three types topologies that every neural network must
follow the one of the following:
1. single-level topology
2. multi-level topology
3. recurrent topology
11. 1. SINGLE LEVEL:
• The simplest kind of neural network is a single-layer
network, which consists of equal no. of input and
output nodes.
2. MULTI LEVEL:
• In multi-level, each neuron in one layer has directed
connections to the neurons of the subsequent layer
3. RECURRENT:
• A recurrent neural network (RNN) is a class of artificial
neural networks where connections between units form a
directed cycles.
12. LEARNING METHODS OF
NEURON
• Neurons in neural networks will learn about the working pattern
of the new task.
• Next time, when the same task is given to perform, it
automatically generates output without wasting of time.
• There are three types of learning methods. they are
1. supervised learning
2. unsupervised learning
3. reinforcement learning
13. APPLICATIONS
• Mobile computing
• Forecasting
• Character recognition
• Traveling salesman problem
• Medical diagnosis
• Quality control
• Data mining
• Game development
• Pattern recognition.
14. MERITS
DEMERITS
• No need to write any algorithms.
• Work by learning.
• Work will be automatically shared.
• Robust.
• Neural networks works efficiently.
• Needs to understand before working with neural
networks.
• Requires high processing time for large neural networks.
• Noisy data.
• Takes large time for connecting neurons.
15. CONCLUSION
The computing world has a lot to gain from neural
networks. Their ability to learn by example makes
them very flexible and powerful. Furthermore there
is no need to devise an algorithm in order to
perform a specific task.