Yapay Sinir Ağları Nedir

Yapay Sinir Ağları Hakkında özet bilgiler

Fann Nedir

Fast Artifical Neural Networks Kütüphanesi hakkında

FannTool

Nedir Ne işe yarar Nasıl Kullanırız

What are Artificial Neural Networks ?

short info about Artificial Neural Networks

What is FANN ?

about Fast Artifical Neural Networks library

FannTool

What is and How to use

8 Ekim 2015 Perşembe

The Use of Artificial Neural Networks to Assess the Capacity of Transport Measures


 

In the area of logistics management both managers and engineers rely primarily on proven computational
algorithms, for this reason, it is often difficult to convince them to the use of artificial neural networks in solving decision problems. The paper presents the possibilities of using the FANN library in building of a computer application applied in the area of logistics. The possibilities of the component are presented on the example of applications of artificial neural networks to estimate the capacity of transport vehicles based on their dimensions. The example presented in the work was solved with the use of a multi-network Layered Perceptron. The example depicted not only the possibility of using artificial neural networks for solving poorly structured tasks but also practical application of the TFannNetwork component.
....

Fast Artificial Neural Network library (FANN) is an open-source project that implements a
multi-layer one-way neural network networks with support for both full and weakly
connected networks [14]. FANN is easy to use, comprehensive, well documented and fast in
acting [15], [16]. There are links to over 15 programming languages, including Delphi 7
program.
TFannNetwork is a component of Delphi (created by Pereira Maia) that connects the
application with FANN library. Undoubtedly it is not necessary to install TFannNetwork to
use FANN in Delphi but the component makes the library more friendly for Delphi
environment [14].

The Use of Artificial Neural Networks to Assess the Capacity of Transport Measures

Artur Duchaczek / Dariusz Skorupka

General Tadeusz Kościuszko Military Academy of Land Forces Faculty of Management

SSP - JOURNAL OF CIVIL ENGINEERING Vol. 10, Issue 1, 2015


Staged Tuning: A Hybrid (Compile/Install-time) Technique for Improving Utilization of Performance-asymmetric Multicores






Emerging trends towards performance-asymmetric multicore pro-
cessors (AMPs) are posing new challenges, because for effective
utilization of AMPs, code sections of a program must be assigned
to cores such that the resource needs of the code sections closely
match  the  resources  available  at  the  assigned  core.  Computing
this assignment can be difficult especially in the presence of un-
known or many target AMPs. We observe that finding a mapping
between the code segment characteristics and the core character-
istics is inexpensive enough, compared to finding a mapping be-
tween the code segments and the cores, that it can be deferred un-
til installation-time for more precise decision. We present staged
tuning which combines extensive compile time  analysis  with in-
telligent binary customization at install-time. Staged tuning is like
staged compilation, just for core assignment. Our evaluation shows
that staged tuning is effective in improving the utilization of AMPs.
We see a 23% speedup over untuned workloads.

 
.....
Neural Network Training
We  use  the  FANN  library  [32]  for constructing and training our neural networks. In our experiments,we  compute  a  grouping  (i.e.,  core  assignment)  for  each  individual benchmark.

Staged Tuning: A Hybrid (Compile/Install-time) Technique for Improving Utilization of Performance-asymmetric Multicores

tyler Sondag ( Intel Labs ) Hridesh Rajan ( Iowa State University )