A SEMINAR ON CELLULAR NEURAL NETWORK
YOGESH KUMAR GURJAR
ELECTRONICS AND COMMUNICATION
4 TH YEAR STUDENT
Cellular Neural Network is a revolutionary concept
and an experimentally proven new computing
paradigm for analog computers. Looking at the
technological advancement in the last 50 years ;
we see the first revolution which led to pc
industry in 1980’s, second revolution led to
internet industry in 1990’s cheap sensors & mems
arrays in desired forms of artificial eyes, nose, ears
etc. this third revolution owes due to C.N.N. This
technology is implemented using CNN-UM. and
is also used in image processing. It can also
implement any Boolean functions.
Cellular neural networks (CNN) are a regular, single
or multi-layer, parallel computing paradigm similar
to neural networks, with the difference that
communication is allowed between neighbouring
processing structures with analog nonlinear dynamic
Each cell is made up of linear capacitor, non linear
voltage controlled current source, resistive linear
Cellular neural network (CNN) is a locally connected,
analog processor array which has two or more
dimensions. A standard CNN architecture consists of an
M N rectangular array of cells C(i, j) with Cartesian
coordinate (i, j), where i = 1..M, j = 1..N
ARCHITECTURE OF CNN
The state of a cell depends on inter-connection
weights between the cell and its neighbours. These
parameters are expressed in the form of the template.
The CNN Universal Machine (CNN-UM) is based on a
First programmable analog processor array computer
with its own language and operation system whose VLSI
implementation has the same computing power as a
supercomputer in image processing applications.
The extended universal cells of CNN-UM are controlled
by global analogic programming unit (GAPU), which has
analog and logic parts: global analog program register,
global logic program register, switch configuration
register and global analogic control unit. Every cell has
analog and logical memory.
Universal Machine (CNN-UM)
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 8 nearest surrounding neighbors.
Each cell is characterized by uij, yij and vij being the
input, the output and the state variable of the cell respectively.
The output is related to the state by the nonlinear equation:
yij = f(vij) = 0.5 (| vij + 1| – |vij – 1|)
CHARACTERISTICS OF THE CNN
High speed target recognition, tracking.
Real time visual inspection of manufacturing
Cheap sensors and mems arrays are in the desired
forms of artificial eyes, nose, ears, taste &
realization of telepathy.
Intelligent vision capable of recognition of contextsensitive & moving scenes as well as applications
requiring real time fusing of multiple modalities
such as multi spectral images involving
infrared, long wave-infrared and polarized lights.
PDE based in modern image processing techniques
are becoming most challenging & important for
analogic C.N.N. computers. A major challenge yet
not solved by any existing technology is to build
analogic adaptive sensor computer where sensing &
computing understanding are fully integrated on a