Scribd
Upload
43 views26 pages

ANN Lecture 01

Uploaded by

Shashika Udara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
43 views26 pages

ANN Lecture 01

Uploaded by

Shashika Udara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 26

Lecture 01

Artificial
Neural
Networks
Evaluation

Quizzes ( 3 ) 10 %
Assignment ( 2 ) 10 + 5 %
Group Project 15 %
End Semester 60 %
Recommended
Reading
Session Outline
1.What is Artificial Neural Network ?

2.Architecture of an Artificial Neural


Network.

3.Cons and Pros of ANN

4.Applications of ANN
What is Artificial Neural Networks ?
➢ An Artificial Neural Network ( ANN ) is an
information processing paradigm that is inspired by
the way biological nervous system, such as the
brain process information.

➢ It consists of large number of highly interconnected


neurons in it to carry information.
What is a Neuron ?
➢ A biological neuron is the basic unit of the human
brain, which is specially designed to transmit
information to other nerve cells, muscle, etc.
What is a Neuron ? ( Cont .. )
➢ A neuron takes some inputs (through dendrites)
processes them, and provides outputs (through
axons)
What is a
Neuron ?
What is a Neuron ? ( Cont .. )
➢ If the combination of input electrical signals is
above a certain threshold, it results in firing or
activation of the neuron.

➢ The same principle of firing/activation is used in


artificial neurons as well. The Artificial Neural
Networks (ANN) is inspired by this arrangement of
biological neurons in our brains and its basic unit is
called a Neuron or a Perceptron.
Parts of a Neuron & their functions
Function of Dendrite
➢ It receives signals from other neurons.

Soma (cell body)


➢ It sums all the incoming signals to generate input.

Axon Structure
➢ When the sum reaches a threshold value, neuron fires
and the signal travels down the axon to the other
neurons.
Parts of a Neuron & their functions
Synapses Working
➢ The point of interconnection of one neuron
with other neurons. The amount of signal
transmitted depends upon the strength
(synaptic weights) of the connections.
What can Neural Network do ?
What is Artificial Neural Networks ?

➢ Dendrites from Biological Neural Network represent Inputs


in Artificial Neural Networks, Cell nucleus (soma) represents
Nodes, Synapse represents Weights, and Axon represents
Output.
Relationship between Biological Neural
Network and Artificial Neural Network

BNN ANN
Soma Node
Dendrites Input
Synapse Weights or
Interconnections
Axon Output
Architecture of an Artificial Neural Network
➢ A Neural network that consists of a large number of
artificial neurons, which are termed units arranged in
a sequence of layers

➢ Artificial Neural Network primarily consists of three


layers:
Architecture of an Artificial Neural Network
➢ Input Layer :
As the name suggests, it accepts inputs in several different formats
provided by the programmer.

➢ Hidden Layer :
The hidden layer presents in-between input and output layers. It performs
all the calculations to find hidden features and patterns.

➢ Output Layer :
The input goes through a series of transformations using the hidden layer,
which finally results in output that is conveyed using this layer.
Model of an Artificial Neural Network
Model of an Artificial Neural Network
Model of an Artificial Neural Network
➢ For the above general model of artificial
neural network, the input can be calculated
as follows
Model of an Artificial Neural Network
➢ The output can be calculated by applying the
activation function over the net input.
Advantages of an Artificial Neural Network
➢ Parallel processing capability
➢ Fault Tolerance
➢ ANNs have the ability to learn and model non-
linear and complex relationships
➢ ANNs can generalize & helps in predict unseen
data.
➢ Capability to work with incomplete knowledge
Disadvantages of an Artificial Neural
Network
➢ Hardware dependence
➢ Determination of proper network structure
➢ Duration of development
➢ Unrecognized behavior of the network
➢ Amount of data
Artificial Neural Network on Applications
➢ Aerospace-Generally, we use ANN a for Autopilot
aircrafts. They used for aircraft fault detection.

➢ Military -In various ways, we use ANN an in the


military. Such as Weapon orientation and steering,
target tracking.

➢ Electronics -Basically, we use an Artificial neural


network in electronics in many ways. That are code
sequence prediction, IC chip layout, and chip failure
analysis.
Artificial Neural Network on Applications
➢ Medical-As medical has too many machines. That use
in various ways. Such as cancer cell analysis, EEG and
ECG analysis.

➢ Speech -We use ANN in speech recognition and


speech classification.

➢ Telecommunications- Generally, it has different


applications. Thus, we use an Artificial neural
network in many ways. Such as image and data
compression, automated information services.
Refer
➢ https://towardsdatascience.com/the-differences-
between-artificial-and-biological-neural-networks-
a8b46db828b7
“
Thank You !!!!!

You might also like