Login Register



Auto-login on future visits

Forgot your password?

11.04.2014

April 2014 perClass training course

pattern recognition training course for industry'The last edition of the perClass course took place in the week 7-11 April in Delft. This time, we welcomed researchers from UK, Belgium and The Netherlands working on diverse applications including hyperspectral imaging, high-speed computer-vision and bio-medical signal processing.

Read more...
(0) Comments

04.04.2014

In-house training course in Wageningen

Tomato classification from hyperspectral image' In the beginning of April, we organized an in-house training course in Wageningen UR (Plant Sciences Group). It was a great to work with this highly experienced team specializing in agricultural automation. Our course covered the entire pattern recognition system design life-cycle from problem definition, feature selection, classifier training to application-specific performance optimization and real-time deployment.

Read more...
(0) Comments

02.12.2013

Ever wished for a faster Gaussian mixture classifier?

fast Gaussian mixture classifier in Matlab' Oh yes we did! In many of our projects, the best classifier is something a bit more flexible than a simple model but not too much more. Non-parametric classifiers such as k-NN or Parzen are powerful but, for large problems, quickly become a bottleneck due to their execution speed.

Read more...
(0) Comments

11.11.2013

perClass course October 2013

participants of the October 2013 perClass pattern recognition course 'Machine Learning for R&D Specialists' In our October course, we welcomed participants coming from Israel, Nigeria, UK, Poland and The Netherlands, again a very multi-cultural group.

This time we had a strong presence of academic participants. They are challenged in their research projects to develop medical diagnostic applications, quality control systems and image-based emotion classification. As we have learned, their shared motivation to join the course was the interest to go beyond theory and leverage machine learning as a working tool.  We have discussed many aspects of classifier design, ranging from annotation and interactive visualization of their data sets, to feature selection, preventing classifier overtraining and performance optimization.

It was very enjoyable to get to know each other, learn not only about the specific projects but also different company cultures, and share different views and experiences.  Thank you guys for coming, it was really a nice experience for us at PR Sys Design as well.

Read more...
(0) Comments

24.07.2013

Do you also avoid neural nets for large data sets?

scalable neural network classifier in Matlab' When designing a classifier for a problem with million samples, would you consider neural network as an option? Or do you also believe the common knowledge that training an accurate network classifier for such problems is too slow to be practical? See what we found, designing a scalable network implementation in perClass 4!

Read more...
(0) Comments

Page 1 of 10 pages  1 2 3 >  Last »