A high bit resolution FPGA implementation of a FNN with a new algorithm for the activation function

The Modeling and Hardware Implementation of Semiconductor Circuit Elements by Using ANN and FPGA

“…The first comparison item is implementation area. The proposed FPGA-based intelligent hardware implementation [7,[10][11][12][13] is very suitable method for the semiconductor circuit elements.…”

“…The execution time and hardware space used is excessively better on FPGA [7,9,10,13] when comparing the classical electronic chips. FPGA chips have endless reconfigurations advantages according to ASIC's, CPLD's or DSP's.…”

“…Artificial neural networks (ANNs) have been commonly used in many fields for solving the difficult and complex problems. The most widely used ANN is the multi-layer perceptron (MLP) [7,8]. The parallel structure of the neural network is very important feature for real-time implementations.…”

Accelerated Artificial Neural Networks on FPGA for Fault Detection in Automotive Systems

“…In [5], the authors present an FPGA implementation of the reactive routing scheme for improving the performance of mobile ad-hoc networks using a 2-4-1 MLP ANN. Floating point representation was explored for an adaptive activation function and for the entire compute structure in [10], [11], providing better accuracy for the system. Among others, [7], [12] discuss the use of ANNs for hard-real-time embedded applications like fault-detection, and real-time tracking applications in automotive and defence systems.…”

Automatic general-purpose neural hardware generator

“…The common use of the hyperbolic tangent and other sigmoid functions, though simple in terms of software, is very difficult to implement in hardware and has been the object of study of many researchers [5][6][7][8][9][10][11][12][13][14][15]. As a result of this difficulty, most of the implementations found in the literature use oversimplified activation functions [6,7,9].…”