English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Artificial Neural Networks (ANNs) base their processing capabilities in parallel ar chitectures. This makes them useful to solve pattern recognition, system id entification and control problems. This work focuse s the configuration of a Field Programmable Gate Arra y (FPGA) to realize an Activation Function (AF) utilized in ANNS. The most popular AF is the Log-Sigmoid function, which has different possibilities of realizing in digital hardware. In particular a two parallel processes approach, in order to optimize hardware resources of the used FPGA device, is pres ent d here. The first process consists in a fixed-p oint computation of 2 that requires minimal hardware resources. The seco nd process executes a second order symmetric polynomial function extended to adder out put of an Artificial Neuron (AN). The log-sigmoid function has been obtained multiplying the function s obtained by two parallel processes. The second process has been implemented by means the custom de velop d sfloat24 math library. This function is one the most used activation funct ion in the ANNS because its differentiable nature that makes it compatible with any classical back propaga tion algorithm. The simulation results show that the proposed appro ach of implementing the log-sigmoid activation function is feasible, and it outperforms by high-sp eed response.

A Novel Approach for Implementing of a Log-Sigmoid Function on a FPGA Device Using the Sfloat24 Math Library – An Modelling –