| Summary: | Supervised pattern recognition is the process of mapping patterns to class labelsthat define their meaning. The core methods for pattern recognitionhave been developed by machine learning experts but due to their broadsuccess an increasing number of non-experts are now employing andrefining them. In this perspective I will discuss the challenge ofcorrect validation of supervised pattern recognition systems, in particular whenemployed by non-experts. To illustrate the problem I will give threeexamples of common errors that I have encountered in the lastyear. Much of this challenge can be addressed by strict procedure invalidation but there are remaining problems of correctlyinterpreting comparative work on exemplary data sets, which I willelucidate on the example of the well-used MNIST data set of handwrittendigits.
|
|---|
