Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Genetic Algorithm

Sortuj według:

Ogranicz wyniki do:

Embryonic Architecture with Built-in Self-test and GA Evolved Configuration Data

100%

Malhotra G. , Duraiswamy P. , Kishore J. K.

tom Vol. 69, No. 2

211--217

The embryonic architecture, which draws inspiration from the biological process of ontogeny, has built-in mechanisms for self-repair. The entire genome is stored in the embryonic cells, allowing the data to be replicated in healthy cells in the event of a single cell failure in the embryonic fabric. A specially designed genetic algorithm (GA) is used to evolve the configuration information for embryonic cells. Any failed embryonic cell must be indicated via the proposed Built-in Selftest (BIST) the module of the embryonic fabric. This paper recommends an effective centralized BIST design for a novel embryonic fabric. Every embryonic cell is scanned by the proposed BIST in case the self-test mode is activated. The centralized BIST design uses less hardware than if it were integrated into each embryonic cell. To reduce the size of the data, the genome or configuration data of each embryonic cell is decoded using Cartesian Genetic Programming (CGP). The GA is tested for the 1-bit adder and 2-bit comparator circuits that are implemented in the embryonic cell. Fault detection is possible at every function of the cell due to the BIST module’s design. The CGP format can also offer gate-level fault detection. Customized GA and BIST are combined with the novel embryonic architecture. In the embryonic cell, self-repair is accomplished via data scrubbing for transient errors.

Performance investigation and element optimization of 2D array transducer using Bat Algorithm

100%

Tantawy D. M. , Eladawy M. , Hassan M. A. , Mubarak R. , Tantawy D. M. , Eladawy M. , Hassan M. A. , Mubarak R.

IMPLEMENTING EVOLUTIONARY ALGORITHM INTO TRAINING SINGLE-LAYER ARTIFICIAL NEURAL NETWORK IN CLASSIFICATION TASK

86%

Płaczek S.

nr 3

377-388

The article proposes implementing a modified version of genetic algorithm in a neural network, what in literature is known as “evolutionary algorithm” or “evolutionary programming”. An Evolutionary Algorithm is a probabilistic algorithm that works in a set of weight variability of neurons and seeks the optimal value solution within a population of individuals, avoiding the local maximum. For chromosomes the real value variables and matrix structure are proposed to a single-layer neural network. Particular emphasis is put on mutation and crossover algorithms. What is also important in both genetic and evolutionary algorithms is the selection process. In the calculation example, the implementation of theoretical considerations to a classification task is demonstrated.