scholarly journals Cellular Automata for Pattern Recognition

Author(s):  
Sartra Wongthanavasu ◽  
Jetsada Ponkaew

2002 ◽  
pp. 875-907
Author(s):  
P TZIONAS ◽  
I ANDREADIS




Author(s):  
KENICHI MORITA ◽  
SATOSHI UENO ◽  
KATSUNOBU IMAI

A PCAAG introduced by Morita and Ueno is a parallel array generator on a partitioned cellular automaton (PCA) that generates an array language (i.e. a set of symbol arrays). A "reversible" PCAAG (RPCAAG) is a backward deterministic PCAAG, and thus parsing of two-dimensional patterns can be performed without backtracking by an "inverse" system of the RPCAAG. Hence, a parallel pattern recognition mechanism on a deterministic cellular automaton can be directly obtained from a RPCAAG that generates the pattern set. In this paper, we investigate the generating ability of RPCAAGs and their subclass. It is shown that the ability of RPCAAGs is characterized by two-dimensional deterministic Turing machines, i.e. they are universal in their generating ability. We then investigate a monotonic RPCAAG (MRPCAAG), which is a special type of an RPCAAG that satisfies monotonic constraint. We show that the generating ability of MRPCAAGs is exactly characterized by two-dimensional deterministic linear-bounded automata.



Author(s):  
Niloy Ganguly ◽  
Pradipta Maji ◽  
Arijit Das ◽  
Biplab K. Sikdar ◽  
P. Pal Chaudhuri


2013 ◽  
Vol 7 ◽  
pp. 857-866 ◽  
Author(s):  
B. Luna-Benoso ◽  
R. Flores-Carapia ◽  
C. Yanez-Marquez




1993 ◽  
Vol 01 (01) ◽  
pp. 59-68 ◽  
Author(s):  
G. GRÖSSING

The concept of Nonlocal Computation as emergent property of coupled neuronal modules is introduced with the aid of quantum cellular automata (QCA). Various features of QCA evolution indicate their possible relevance for realistic simulations of neuronal systems. To these features belong the appearance of periodic oscillations in a system of even less than 10 modules, evolutionary strategies like selection and equifinality, the multiplexing of “temporal codes”, and high fault tolerances in pattern recognition tasks.



1993 ◽  
Vol 70 (1-2) ◽  
pp. 145-177 ◽  
Author(s):  
Raghu Raghavan


Author(s):  
Niloy Ganguly ◽  
Arijit Das ◽  
Pradipta Maji ◽  
Biplab K. Sikdar ◽  
P. Pal Chaudhuri


1993 ◽  
Vol 5 (5) ◽  
pp. 750-766 ◽  
Author(s):  
A. Norman Redlich

Factorial learning, finding a statistically independent representation of a sensory “image”—a factorial code—is applied here to solve multilayer supervised learning problems that have traditionally required backpropagation. This lends support to Barlow's argument for factorial sensory processing, by demonstrating how it can solve actual pattern recognition problems. Two techniques for supervised factorial learning are explored, one of which gives a novel distributed solution requiring only positive examples. Also, a new nonlinear technique for factorial learning is introduced that uses neural networks based on almost reversible cellular automata. Due to the special functional connectivity of these networks—which resemble some biological microcircuits—learning requires only simple local algorithms. Also, supervised factorial learning is shown to be a viable alternative to backpropagation. One significant advantage is the existence of a measure for the performance of intermediate learning stages.



Sign in / Sign up

Export Citation Format

Share Document