cellular neural networks
• 0 Vote(s) - 0 Average
• 1
• 2
• 3
• 4
• 5
 seminar class Active In SP Posts: 5,361 Joined: Feb 2011 23-04-2011, 04:40 PM Presented by DEEPA RANI PATRO   techsem_ppt_191.ppt (Size: 464.5 KB / Downloads: 46) CELLULAR NEURAL NETWORK INTRODUCTION  Cellular Neural Networks (CNNs) is a paradigm of mostly locally connected networks of simple non-linear processors in discrete N-dimensional spaces.  Cells are multiple input-single output processors, all described by one or just some few parametric functionals which control the cell inter-connection strength.  Cell interconnect is local, meaning that all connections between cells are within a specified radius, where distance is measured topologically which allows also to obtain global processing.  Connections can also be time-delayed to allow for processing in the temporal domain.  This exhibits space-invariance property.  Dynamics are usually • Continuous-Time CNN (CT-CNN) processors Discrete-Time CNN (DT-CNN) processors FEATURES OF CNN  The CNN can be defined as an M x N type array of identical cell arranged in a rectangular grid.Each cell is locally connec-ted to its 8 nearest surrounding neighbors.  Each cell is characterised by uij, vij and xij being the input, The output and the state variable of the cell respectively.  The output is related to the state by the nonlinear equation: vij = f(xij) =o.5(| xij + 1| - | xij - 1|)  The state transition of the cell C(i,j) is governed by the following differential equation:  The coefficients are known as cloning templates which are generally non-linear and time and space variant operators. Structure of single CNN cell  The node voltage Vxij is called the state of the cell .  The node voltage Vuij is called the input of c(i,j) .  The node voltage Vyij is called the output. DISCRETE TIME-CNN  A DT-CNN poses a regular grid of locally connected cells.  The DT-CNN is a clocked system; whose dynamics are described by a set of discrete equations.  A cell ‘C’ is identified by the coordinate of its position in the grid, i.e. row Ci and column Cj and communicates directly with all the neighbor cells belonging to the r-neighborhood. The character d represents any cell belonging to the neighborhood of cell C, including C itself.  Equation below depicts the dependencies of state of a cell C, denoted xc on input ud and the time-variant output yd at a discrete time k. The functionality of DT-CNN cell is depicted by CNN-UNIVERSAL MACHINE  It is the first spatiotemporal analogic array computer.  The two different operations are • continuous-time, continuous valued spatio-temporal nonlinear array dynamics (2-d\$3-darrays) local & • global logic • As both analog & logic operations are mixed and embedded in array computer, this type of computing is called analogic.
 hemanthbl Active In SP Posts: 1 Joined: May 2011 02-05-2011, 01:37 PM send me the full report of "cellular neural network"