Trabalho apresentado em evento
Approximation of hyperbolic tangent activation function using hybrid methods
Fecha
2013-09-16Registro en:
2013 8th International Workshop on Reconfigurable and Communication-Centric Systems-on-Chip, ReCoSoC 2013.
10.1109/ReCoSoC.2013.6581545
2-s2.0-84883659156
Autor
Universidade do Estado de Mato Grosso (UNEMAT)
Universidade Estadual Paulista (Unesp)
Resumen
Artificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers by several factors, such as floating point precision, nonlinear activation function, performance and area used in FPGA. The contribution of this work is the approximation of a nonlinear function used in ANN, the popular hyperbolic tangent activation function. The system architecture is composed of several scenarios that provide a tradeoff of performance, precision and area used in FPGA. The results are compared in different scenarios and with current literature on error analysis, area and system performance. © 2013 IEEE.
Materias
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Relative freedom and ascesis: the function of reason in Schopenhauer’s ethics
Salviano, Jarlee Oliveira Silva -
Theories of remembering: causalism, simulationism, and functionalism
Sant'Anna, André Rosolem; Michaelian, Kourken -
Rotational states of asymmetric molecules revisited: matrix evaluation and generating function of lame functions
Ley Koo, Eugenio; Méndez Fragoso, R.