Advanced applications of artificial intelligence and neural networks
1. SAMBHRAM INSTITUTE OF TECHNOLOGY, BENGALURU
Department of Electronics & Communication Engineering
SEMINAR Presentation
on
ADVANCED APPLICATION OF
ARTIFICIAL INTELLIGENCE AND
NEURAL NETWORKS
Presentation by
RAJARAJESHWARI K DIVATE (1ST13EC727)
VIII Semester B.E.
Seminar coordinator Class Coordinator
Dr. C.V. Ravi Shankar S. Sowndeswari
HOD, Dept of ECE, SaIT Asst.Prof. Dept. ECE, SaIT
2. Introduction to AI
The ability to acquire and apply
knowledge and skills is called
intelligence.
This phenomenon is exhibited by
human brain.
Artificial intelligence(AI) is
intelligence exhibited by machines.
It is the theory and development of
computer systems able to perform
tasks normally requiring human
intelligence .
Such as visual reception , speech
recognition, decision making, and
translation between languages.
3. Biological neural network
The basic computational unit in the
nervous systyem is the nerve cell or
neuron.
A neuron has:
dendrites (inputs)
cell body
axon (output)
The human brain contains about 10
billion neurons.
On average , each neuron is connected
to other neurons through about 10000
synapses.
Figure : Structure of a neuron
4. Artificial neural network
ANN is a computer system
modeled on the human brain and
nervous system.
An ANN is an interconnected
group of nodes, akin to vast
network of neurons in a brain.
Each circular node in the figure
represents an artificial neuron
and an arrow represents a
connection from the output of
one neuron to the input of
another. Figure: Artificial neuron
5. Terminology
Biological terminology ANN terminology
Neuron Node/unit cell/neurode
Synapse Connection/edge/link
Synaptic efficiency Connection strength/weight
Firing frequency Node output
6. Types of neural network
Fixed networks
In which the weights cannot be changed, that is
dW/dt=0. In such networks, the weights are fixed a
priori according to the problem to solve.
Adaptive networks
Which are able to change their weights, that is
dW/dt not=0.
10. Hopfield network
A hopfield network is a form of
recurrent ANN invented by john
Hopfield in 1982.
It can be seen as a fully connected
single layer auto associative
network.
Hopfield nets serve as content
addressable memory systems with
binary threshold nodes.
Hopfield net
11. Hopfield networks are constructed from artificial
neurons.
These artificial neuron have N inputs. With each input
i there is a weight wi associated.
They have an output. The state of the output is
maintained, until the neuron is updated.
12. A HNN consists of a set of
neurons where each neuron
corresponds to a pixel of the
different image and is connected
to all the neurons in the
neighbourhood.
The output of the neuron is
feedback to each of the other
neurons in the network.
The number of feedback loops is
equal to the number of neurons.
There is no self feedback loop.
13. A recurrent network with all nodes connected to all
other nodes.
Nodes have binary outputs (either 0,1 or 1,-1)
Weights between the nodes are symmetric.
No connection from node to itself is allowed.
Nodes are updated asynchronously (the nodes are
selected at random)
The network has no hidden layers or nodes.
14. Energy
Hopfield defined the energy function of the network
by using the network architecture, i.e.,
the number of neurons
their output functions
threshold values
connection between neurons
The strength of the connections
Thus the energy function represents the complete
status of the network.
15. Contd…
Hopfield has also shown that at each iteration of the processing
of the network, the energy value decreases and the network
reaches a stable state when its energy value reaches a
minimum.
The energy function E of the discrete model is given by
Where i,j,k are the variables
W is the weight
V is the output the neuron
I is external input bias
16. Features of HNN
HNN can perform the functions of memory recall in a
manner analogous to the way the brain functions.
In addition, pattern recognition, solving linear
programming problems and solving combinatorial
optimization problems(COPs).
Simple technical implementation using electronic or
optical device.
17. Applications of ANN
ANN has been successfully applied to broad spectrum
of data-intensive applications like financial, data
mining, operational analysis, industrial, sales and
marketing.
One such important application is in the field of
medical science. Such as
Medical diagnosis
Detection and evaluation of medical phenomena
Patient’s length of stay forecasts
Treatment cost estimation
18. Lung cancer detection using ANN
The early detection of the lung cancer is a challenging
problem, due to the structure of the cancer cells.
The manual analysis of the sputum sample is time
consuming, inaccurate and requires intensive trained
person to avoid diagnostic errors.
There aremany techniques to diagnosis lung cancer,
such as chest radiograph(x-ray), computed
tomography(CT), magnetic resonance imaging(MRI
scan) and sputum cytology.
However, most of these techniques are expensive and
time consuming.
19. Most of these techniques are detecting the lung cancer
in its advanced stages, where the patient’s chance of
survival is very low.
Hence, Hopfield neural network segmentation
method is used for segmenting sputum colour images
to detect the lung cancer in early stages.
The segmentation results will be used as a base for a
Computer Aided Diagnosis ( CAD)system for early
detection of lung cancer.
This method is designed to classify the image of N
pixels.
20. The HNN segmentation algorithm
1. Initialize the input of neurons to random values.
2. Apply the input- output relation given by
to obtain the new output value for each neuron,
establishing the assignment of pixel to classes.
21. 3. Compute the centroid for each class as follows:
4. Solve the set of differential equation
to update the input of each neuron:
5. Repeat from step 2 until convergence then terminate
22. Conclusion
The HNN algorithm is applied with the specification
mentioned above to one thousand sputum colour
images and maintained the result for further
processing in the following steps.
This algorithm could segment 97% of the images
successfully in nuclei, cytoplasm regions and clear
background
Furthermore, HNN took short time to achive the
desired results.
By experiment, HNN needed less than 120 iterations to
reach the desired segmentation result in 36 seconds.