You are on page 1of 20

CELLULAR NEURAL NETWORK

VISHAL DWIVEDI
ROLL NO.1109131118
What is a Neural Network?
An Neural Network (NN) is an information
processing paradigm that is inspired by the way
biological nervous systems, such as the brain, process
information.
It is composed of a large number of highly
interconnected processing elements (neurones or cell
or node) working in unison to solve specific
problem.
Similarity between Neuron and Cell
ABOUT CNN IN GENERAL
In 1988 papers from Lion O. Chua introduced the
concept of Cellular Neural Network .
CNN can be defined as 2D or 3D arrays of mainly
locally connected non-linear dynamical system called
cells whose dynamics are functionally determined by
a small set of parameters which control the cells inter-
connection strength(Chua).


Basic Characteristics of CNN
The CNN can be defined as an M x N type array of
identical cells arranged in a rectangular grid. Each
cell is locally connected to its nearest surrounding
neighbors.
Each cell is characterized by u
ij
, y
ij
and x
ij
being
the input, the output and the state variable of the
cell respectively.
The output is related to the state by the nonlinear
equation:
y
ij
= f(x
ij
) = 0.5 (| x
ij
+ 1| |x
ij
1|)
Rectangular Grid showing CNN
CNN Cells
CNN cells are governed by the equation
shown below
x
ij
is the state of cell (i,j)
y
kl
is the output of cell (k,l)
u
kl
is the input to cell (k,l)
z
ij
is the threshold of cell (i,j)
C(i,j) is the set of cells in the CNN
S
r
(i,j) is the set of cells in the sphere of influence of cell
(i,j)
A(i,j; k,l) and B(i,j; k,l) are the feedback and input synaptic
operators respectively

ij
j i S l k C
kl
j i S l k C
kl ij ij
z u l k j i B y l k j i A x x
r r


) , ( ) , ( ) , ( ) , (
) , ; , ( ) , ; , (
Functional Block scheme of a Cell
y=output of a particular cell
x=cells initial state
u=input of cell

Templates
The functionality of the CNN array can be
controlled by the cloning template A, B, I
Where A and B are (2r+1) x (2r+1) real
matrices
I is a scalar number in two dimensional
cellular neural networks.

Logical AND Template
This template creates
the pixel wise AND of
the initial state and the
input
The progression of
images shows the input
and initial image,
followed by the output
at a series of times

Classification of CNN
Continuous Time CNN
Discrete Time CNN
Continuous Time CNN
Chua & Yangs CNN(CY-CNN)
Linear Cloning Template CNN
Full Range CNN
Linear Threshold/Feed-Forward CNN
Polynomial CNN
Non-uniform Processor CNN
Several Other CNN
Discrete time CNN
Multi-valued CNN
CNN with Local Logic(CNNLL)
Why Use CNN?
CNN with their remarkable ability to derive meaning
from complicated data can be used to extract patterns
and detect trends that is too difficult to be detected by
human or other computer technique.
Adaptive learning
Self Organisation
Real Time Operation
Fault Tolerance via Redundant Information Coding
CNN Applications
CNN Processors are versatile platform used for variety
of applications such as
Image Processing
Generation and Analysis of patterns and textures
Chaotic Communication using CNN processors

Planning Flowchart of Motion
CNN versus Conventional Computers
Conventional Computer
Use algorithmic
approach
These are predictable
Speed is slow in
comparison



CNN
Mimic the human brain
These are not
predictable
Speed is the key factor
for CNN processors
CONCLUSION
A brief overview of CNN is given.
Comparison of CNN and other computational
technique is discussed and it is concluded that they
are not in competition but are complement to each
other.
CNN do not perform miracles ,but if they are
used sensibly can produce some amazing results.
REFERENCES

L.O. Chua, L. Yang, "Cellular Neural Networks: Theory",
IEEE Trans. on Circ. And Syst. CAS-35(10), 1257 (1988)

L. Chua and L. Yang, "Cellular Neural Networks:
Applications" IEEE Trans. on Circuits and Systems,
35(10):1273:1290, 1988.

V. Cimagalli, M. Balsi, "Cellular Neural Networks: A
Review", Neural Nets WIRN Vierti, 1993

You might also like