cellular neural

15
SUMBITTED BY: MUKESH KUMAR M.TECH(2010ECB1026)

Upload: mukesh-bhagat

Post on 02-Jul-2015

677 views

Category:

Technology


2 download

TRANSCRIPT

Page 1: Cellular  neural

SUMBITTED BY:

MUKESH KUMAR

M.TECH(2010ECB1026)

Page 2: Cellular  neural

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.

Page 3: Cellular  neural

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

units only.

processing structures with analog nonlinear dynamic

units (cells).

Each cell is made up of linear capacitor, non linear

voltage controlled current source, resistive linear

circuit element.

Page 4: Cellular  neural

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

Page 5: Cellular  neural
Page 6: Cellular  neural
Page 7: Cellular  neural
Page 8: Cellular  neural
Page 9: Cellular  neural

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.

Page 10: Cellular  neural

The CNN Universal Machine (CNN-UM) is based on aCNN.

First programmable analog processor array computer withits own language and operation system whose VLSIimplementation has the same computing power as asupercomputer in image processing applications.

The extended universal cells of CNN-UM are controlled byglobal analogic programming unit (GAPU), which hasanalog and logic parts: global analog program register,global logic program register, switch configuration registerand global analogic control unit. Every cell has analog andlogical memory.

Page 11: Cellular  neural
Page 12: Cellular  neural

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|)

Page 13: Cellular  neural

High speed target recognition, tracking.

Real time visual inspection of manufacturing processes.

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 context-sensitive & 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.

Page 14: Cellular  neural

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 chip.

Page 15: Cellular  neural

THANKS