Resumo

POLANCO CARRILLO, Franky; ALVAREZ GERONIMO, Daniel  e  MORENO VEGA, Valery. A hardware implementation using Artificial Neural Network for Character Recognition. EAC [online]. 2015, vol.36, n.1, pp. 95-106. ISSN 1815-5928.

 This paper deals with the implementation of an Artificial Neural Network on reconfigurable hardware. The authors developed an application for character recognition using a feedforward backpropagation neural network, developed on an FPGA. In order to carry out such implementation the computational model of the neural network is translated into a FPGA synthesizable model using the Matlab/Simulink environment as well as the System Generator Xilinx tool. The results are illustrated in a prototype developed on an Atlys board. The authors focus the analysis and discussion on the main aspects considered to synthetize an ANN on an FPGA as well as the methodology to follow during such implementation, which are the main contributions of this paper.

Palavras-chave : artificial neural network; characters recognition; FPGA; Xilinx system generator.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )