Non-uniform cellular automata based associative memory: Evolutionary design and basins of attraction

Maji, Pradipta; Chaudhuri, P.P.

doi:10.1016/j.ins.2008.01.004

Cited by 24 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This corresponds to the reports in Maji, et al, 2008, the GMACA provides the best performance of pattern recognition when it is trained with the r max =1 and h max =2. However, the percentage of recognition in testing is also high if the Hamming distance of patterns is less than or equal to 1 and it is decreased sharply when the Hamming distance is greater than 1.…”

Section: Theoremsupporting

confidence: 72%

“…It is one time step process which is different from a reverse engineering technique Maji, et al, 2008) using in GMACA. Reverse engineering technique continues reconstructing attractor basins randomly until arriving at the rule vector with the lowest collision.…”

Section: Design Of Rule Vectormentioning

confidence: 99%

“…The search space complexity in Maji, et al, 2008 is examined under the h max =2 and the r max =1 as described below.…”

Section: Theoremmentioning

confidence: 99%

See 2 more Smart Citations

Cellular Automata for Pattern Recognition

Wongthanavasu¹,

Ponkaew²

2013

Emerging Applications of Cellular Automata

View full text Add to dashboard Cite

Section: Theoremsupporting

confidence: 72%

Section: Design Of Rule Vectormentioning

confidence: 99%

See 1 more Smart Citation

Cellular Automata for Pattern Recognition

Wongthanavasu¹,

Ponkaew²

2013

Emerging Applications of Cellular Automata

View full text Add to dashboard Cite

“…A group of researchers of the Santa Fe institute uses Genetic Algorithm (GA) to evolve CA rules, which are able to solve the problem of the DCT. Another approach is presented in [7] for running a CA rule backwards. In other words, find a CA rule such that the whole of configuration-space is divided into precisely two basins of attraction; one of which consists of all rules with density greater than the critical density q and has as its attractor the state of all 1's, and the other consisting of all other configurations and having as its attractor the state of all 0's.The main problem in this approach is the wide variation in quantitative results obtained when sampling different parts of the attractor basin.…”

Section: B Survey On Dctmentioning

confidence: 99%

Cellular automata based algorithm for image density classification task

Anghelescu

Știrbu

2014

Proceedings of the 2014 6th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

View full text Add to dashboard Cite

In this paper is presented a solution based on a bi-dimensional cellular automata (CA) for image density classification task (DCT). The two necessary properties: density preserving and translation are combined together to obtain the DCT solution. These two properties are achieved using a combination of nine fundamental 2D-CA rules and the proposed solution for DCT has two phases: preprocessing phase and decision phase. The project has been implemented in software using C# programming language and experimental results are presented for images with different sizes. This work is totally related to the idea of understanding the impact of the inherently local information processing of CA on their ability to perform a coordinated computation at the global level, as achieved by an evolutionary process.

show abstract

“…In other words, natural evolution is a local behavior. The information can be globally shared only after a process of diffusion, which is similar to cellular automata [23,35]. An agent is a physical or logical entity that can interact with others, pass information, and react on the received messages.…”

Section: Agent Evolution Algorithm (Aea)mentioning

confidence: 99%