Sayfalar

Cumartesi, Mart 30, 2013

FannTool Web güncellemesi

FannTool 'un sitesinde örnekler yayınlamaya devam ediyoruz.
Bu sefer Yapay Sinir Ağlarının  değişik dallarda  mühendislik hesaplamaları için kullanımını örnekliyoruz.

  1. Barajlarının deformasyonların modellenmesi
  2. Yat Hidrodinamiği -  Yacht Hydrodynamics

Konunun detaylarını ilgili yazılara bırakıp burda şundan bahsetmek istiyorum. 

Mühendislik alanında pek çok değişik empirik formül kullanılır. Kullanımı açısından oldukça pratik olan bu formüllerin. Türetilmesi oldukça zordur. Oysa Bilgisayarın bunca yaygınlaştığı zamanımızda. Deney verileri ile eğitilmiş YSA lar kolaylıkla bunların yerini alabilir...

Cumartesi, Mart 02, 2013

Ordan Burdan Haberler

1) FannTool Sitesine söz verdiğimiz eklemede bulunduk
2)  Veri Madenciliği Kupası Başlıyor ;
      
       DATA MINING CUP competition 2013  
In a few weeks one of the worldwide largest data mining contest the "DATA MINING CUP" competition will start. Last year over 80 international teams from 22 countries participated.

In spring each year the prudsys AG wants to enthuse domestic and international students for intelligent data analysis (data mining) and challenge them to find the best solution to a data mining problem in competition with others.

2013 we want to follow on last year and will place two competition parts again. This year both parts are focussed on the forecast of completing order in online shops.
Besides a classic Data Mining task the second part requires to develop an agent again. More details will be be released with the start of the DMC 2013.

 We are looking forward to your ideas!

 start of registration: March 4, 2013
 start of DMC competition: April 3, 2013
3)  Alman Trafik İşaretleri Yarışması Başladı ;

The "German Traffic Sign Detection" Competition has started!


Results will be presented at IJCNN'13 in Dallas Texas, and FREE REGISTRATION prizes are to be won!


************************
Competition Design
************************
The "German Traffic Sign Detection Benchmark" is a multi-class detection problem in natural images. We do cordially invite you to participate. Our benchmark has the following properties:

* single-image detection problem
* images with zero to four relevant objects
* 900 images (divided in 600 training and 300 evaluation images)
* division in three categories
* industry-relevant application: traffic sign detection

The first competition information was released on December 1, 2012, when the preliminary training data was published. Interested teams are invited to download the training dataset and develop their algorithms based thereon. In February there will be a submission phase where teams are invited to upload their results on a new unannotated test dataset. It will then be possible to immediately compare all competing algorithms via our website.

4) OpenCV 2.4.4 yayınlandı; Java kısmında ve Android portunda epey bir ilerleme var, GPU üzerindeki çalışmalar hem CUDA hemde OpenCL üzerinden devam ediyor....
  •    OpenCV Java bindings are ported from Android to desktop Java! Actually any JVM language will work, see Tutorial for details, and Java or Scala code samples.
  •     Android application framework, samples, tutorials, and OpenCV Manager are improved.
  •     Optimizations for the new NVIDIA Kepler architecture, CARMA platform support and other new optimizations in CUDA.
  •     OpenCL module now builds successfully with various SDKs (from AMD, NVIDIA, Intel and Apple) and runs well on different GPUs (AMD, NVidia, Intel HD4000). A lot of new functionality has been added, tons of bugs fixed, performance of many functions has been significantly improved.
  •     100+ reported problems have been resolved since 2.4.3, thanks everybody who participated!