Translating feed-forward nets to SOM-like maps

• A major disadvantage of feedforward neural networks is still the difficulty to gain insight into their internal functionality. This is much less the case for, e.g., nets that are trained unsupervised, such as Kohonen’s self-organizing feature maps (SOMs). These offer a direct view into the stored knowledge, as their internal knowledge is stored in the same format as the input data that was used for training or is used for evaluation. This paper discusses a mathematical transformation of a feed-forward network into a SOMlike structure such that its internal knowledge can be visually interpreted. This is particularly applicable to networks trained in the general classification problem domain.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering (hsv//eng)

Keyword

feature maps

selforganizing maps

Neural networks

rule extraction

character recognition.

Publication and Content Type

kon (subject category)

ref (subject category)