High precision FPGA implementation of neural network activation functions


Abstract:

The efficient implementation of artificial neural networks in FPGA boards requires tackling several issues that strongly affect the final result. One of these issues is the computation of the neuron's activation function. In this work, a detailed analysis of the FPGA implementations of the Sigmoid and Exponential functions is carried out, in a approach combining a lookup table with a linear interpolation procedure. Further, to optimize board resources utilization, a time division multiplexing of the multiplier attached to the neurons was used. The results are evaluated in terms of the absolute and relative errors obtained and also through measuring a quality factor and the resource utilization, showing a clear improvement in relationship to previously published works.

Año de publicación:

2014

Keywords:

    Fuente:

    scopusscopus

    Tipo de documento:

    Conference Object

    Estado:

    Acceso restringido

    Áreas de conocimiento:

    • Red neuronal artificial
    • Software
    • Ciencias de la computación

    Áreas temáticas de Dewey:

    • Ciencias de la computación
    • Ciencias políticas (Política y gobierno)
    • Física aplicada
    Procesado con IAProcesado con IA

    Objetivos de Desarrollo Sostenible:

    • ODS 9: Industria, innovación e infraestructura
    • ODS 17: Alianzas para lograr los objetivos
    • ODS 4: Educación de calidad
    Procesado con IAProcesado con IA