This topic discusses the rudiments of artificial neural networks

1. ARTIFICIAL
NEURAL
NETWORK

2. 2
CONTENTS
• BIOLOGICAL NEURON
MODEL
• ARTIFICIAL NEURAL
NETWORK
• TYPES OF ANN
• LEARNING
• APPLICATIONS
• ADVANTAGES
• DISADVANTAGES
• CONCLUSION

3. 3
BIOLOGICAL NEURON MODEL

4. 4
• A neuron carries electrical impulses. They are the basic units of the nervous system
and its most important part is the brain.
• Dendrite—It receives signals from other neurons.
• Soma (cell body)—It sums all the incoming signals to generate input.
• Axon—When the sum reaches a threshold value, neuron fires and the signal travels
down the axon to the other neurons.
• Synapses—The point of interconnection of one neuron with other neurons. The
amount of signal transmitted depend upon the strength (synaptic weights) of the
connections.
BIOLOGICAL NEURON MODEL

5. 5
ARTIFICIAL NEURAL
NETWORKS
• An artificial neural network (ANN) is a
computational model based on the
structure and functions of biological
neural networks. Information that
flows through the network affects the
structure of the ANN because a neural
network changes - or learns, in a sense
- based on that input and output.
• ANNs are considered nonlinear
statistical data modeling tools where
the complex relationships between
inputs and outputs are modeled or
patterns are found.
• ANN is also known as a neural network.

6. 6

7. 7

8. 8
• INPUT LAYER—contains those units which
receive input from the outside world on
which network will learn, recognize and
processed.
• OUTPUT LAYER—contains units that
respond to the information about how it’s
learned any task.
• HIDDEN LAYER—These units are in between
input and output layers. The job of hidden
layer is to transform the input into something
that output unit can use in some way.
• In most neural networks , hidden neuron is
fully connected to the every neuron in its
previous layer(input) and to the next layer
(output) layer.
ANN ARCHITECTURE

9. Types of Artificial Neural
Networks
• Multilayer perceptron (MLP)
• Convolutional neural network (CNN)
• Recursive neural network (RNN)
• Long short-term memory (LSTM)
• Recurrent neural network (RNN)
• Sequence-to-sequence models
• Shallow neural networks
• Feedforward Neural Network
9

10. • Supervised Learning—The training data is
input to the network, and the desired output
is known weights are adjusted until output
yields desired value.
• Unsupervised Learning—The input data is
used to train the network whose output is
known. The network classifies the input data
and adjusts the weight by feature extraction
in input data.
• Reinforcement Learning—Here the value of
the output is unknown, but the network
provides the feedback whether the output is
right or wrong. It is semi-supervised learning.
10
LEARNING

11. APPLICATIONS
11
Human Face
Recognition
Ridesharing Apps
Like Uber and Lyft
Handwriting
Recognition
Stock Exchange
Prediction

12.  Storing information on the entire network
 Ability to work with incomplete knowledge
 Having fault tolerance
 Parallel processing capability
 Having a memory distribution
12
ADVANTAGES

13. DISADVANTAGE
S
• Hardware dependence
• Unrecognized behavior of the
network
• The duration of the network is
unknown
• Difficulty of showing the issue to
the network
13

14. CONCLUSION
14
• Artificial neural networks are inspired by the learning processes that take place in biological
systems.
• Biological neural learning happens by the modification of the synaptic strength. Artificial neural
networks learn in the same way.
• The synapse strength modification rules for artificial neural networks can be derived by applying
mathematical optimisation methods.
• Learning tasks of artificial neural networks can be reformulated as function approximation tasks.
• Neural networks can be considered as nonlinear function approximating tools (i.e., linear
combinations of nonlinear basis functions), where the parameters of the networks should be
found by applying optimisation methods.
• The optimisation is done with respect to the approximation error measure.
• In general it is enough to have a single hidden layer neural network (MLP, RBF or other) to learn
the approximation of a nonlinear function. In such cases general optimisation can be applied to
find the change rules for the synaptic weights.