Login Register

Auto-login on future visits

Forgot your password?

Selected participants:


Eighteen editions of the course (since 2012) were attended by participants from organizations in 16 countries.


Summary of internal Philips evaluation for July 2016 course (scale 1 to 5, 5=excellent)

  • Knowledge and expertise of trainer: 4.9
  • Quality of the course material (hands-on, exercises): 4.5
  • The overall level of the content matched by expectations: 4.4
  • Average mark (11 questions): 4.43

"Our team on Vision & Robotics choose to use perClass in our machine vision solutions on a structural base. Therefore we followed the in-house training at Wageningen UR with the whole team of (senior) software researchers. The in-house training was from a very high level, perfectly fitting the market demands. Now we should be able to develop faster with a better score on classification issues in agriculture and food applications. -- Erik Pekkeriet, Senior Project manager at Wageningen UR, The Netherlands

"Thanks again for the excellent course. I gained the right knowledge to delve further into our machine learning problems." -- Dr Stefan Gachter, Leica, Switzerland

"I found the course very informative. I think you have done an excellent job in developing a logical framework, with powerful tools, for tackling pattern recognition problems. The use of examples from real problems is extremely useful in understanding the strengths and limitations of a range of concepts and approaches. Thanks again for the great course!" -- Dr Garry Morrison, DeBeers, South Africa

"A comprehensive course in applying machine learning for classification tasks, providing the relationship between different methods, pointers into when to apply what, and best practices in gradually moving from the simplest applicable approach to more complex methods. The major contribution of this course is the exchange of knowledge gained from years of experience into identifying common pitfalls and the specific ways of fixing them. The perClass tool is used within MATLAB as an interactive configuration editor, after which one applies the exported configuration file directly in the standalone C library." -- Dr.Edgar Reehuis, Incatec, The Netherlands

"When I first arrived in Delft to participate in the perClass course I was already an experienced pattern recognition algorithms developer in the industry. I was not sure what contribution the training will have to my professional growth. Very fast I came to realize I made the right decision. The course has served to break barriers and fixations in my way of thinking that became evident over the years. I've experienced with new methods and processes of development on my own datasets, gained fresh insights and extended my professional toolbox. Carmen and Pavel are very educated and experienced instructors and over many discussions they were always happy to share their fountain of knowledge with us. The course was passed to a small and intimate group in a great atmosphere - the perfect environment for learning.
I feel that I've returned to work as a stronger and more able developer, in better position to handle tougher and more challenging problems. I have no doubt participating in the course has strengthen my professional ability, and I strongly recommend to every PR algorithm developer out there to take part in it. On a personal note - Delft is incredibly beautiful little town and if you still need another reason to participate, visiting it would be it!
-- Barak Almog, Given Imaging INC., Israel.

"perClass course is the fastest way to discover and learn classification methods. The software tools are very well developed and are user friendly, this helps to analyze the data and build industrial classifiers quickly." -- Dr. Wojciech Cieszynski, Wroclaw University of Technology, Poland.

"The 5-day training on 'Machine learning for R&D specialists' has put in a nutshell, the core essentials of the practical application of machine learning to real-world problems. perClass makes building and deploying classifiers more 'visible and exciting' with powerful visual displays. Among many other useful insights, the tricks of using ROC curves in the process of building good classifiers was really amazing. The investment to participate in this training was well worth it!." -- Dr Popoola Oluwatoyin, Nigeria

"perClass is in my opinion the Swiss Army knife of Pattern Recognition: versatile, easy to use (but not superficial), and efficient, enabling you to quickly solve your problems. The perClass course can be described in similar terms: it teaches you how to solve a large range of problems, it is not difficult to follow (but can go very deep when needed), and sharpens your skills at a high pace while at the same time leaving room for relaxed talks and a friendly atmosphere. I especially liked that the course materials, and the hands-on sessions, were partly adapted to the practical needs of the participants. I recommend both the toolbox and the course to anyone doing data analysis." -- Andrei

"The Pattern Recognition course on perClass is a good chance for us to improve our knowledges in a very challenging research area, with many real-life practical applications. The theoretical part but also the exemples and exercises helped us to have a better understanding on the pattern recognition critical issues, in order to be able to desing and generate more complex applications from different real problems. The course structure covered very well the main topics in pattern recognition, actually the main stages in a pattern recognition design. Kind greetings for you for this great chance." -- Sorin

"The perClass course was a huge enrichment for me! The course gives you a large overview of the most common and important classification models and how to build and evaluate a good classifier. It's separated in lectures with following exercises, which is a good solution to directly apply the methods you just learned. The handling of the toolbox is intuitive and easy to learn and the toolbox itself is very powerful can be applied on various tasks. The possibility of bringing your own data and discussing your individual task with the lecturers was very helpful. " -- Beatrice