Constructivist Machine Learning

Schmid, Thomas (2023) Constructivist Machine Learning. In: Compendium of Neurosymbolic Artificial Intelligence :. Frontiers in Artificial Intelligence and Applications . IOS Press. ISBN 9781643684062

Abstract

While neuro-inspired and symbolic artficial intelligence have for a long time been con- sidered ideal complements, approaches to hybridize these concepts often lack an unifying grand theory. The way the philosophical concept of constructivism has been adapted for eductional purposes, however, provides a fruitful source of inspiration for this purpose. To this end, we have developed a framework termed Constructivist Machine Learning, which applies constructivist learning principles and exploits metadata on the grounds of Stachowiak’s General Model Theory in order to bridge the gap between neuro-spired and symbolic approaches. In this chapter, we summarize our previous work in order to introduce the reader to the most important ideas and concepts.