Implementation of a Fast Artificial Neural Network Library

Steffen Nissen
October 31, 2003
Department of Computer Science
University of Copenhagen (DIKU)

Abstract

This report describes the implementation of a fast arti ficial neural network library in ANSI C called fann. The library implements multilayer feedforward networks with support for both fully connected and sparse connected networks. Fann off ers support for execution in fixed point arithmetic to allow for fast execution on systems with no  floating point processor. To overcome the problems of integer overflow, the library calculates a position of the decimal point after training and guarantees that integer overflow can not occur with this decimal point.
The library is designed to be fast, versatile and easy to use. Several benchmarks have been executed to test the performance of the library. The results show that the fann library is signi cantly faster than other libraries on systems without a  floating point processor, while the performance was comparable to other highly optimized libraries on systems with a floating point processor.

Implementation of a Fast Artificial Neural Network Library (fann)