Abstract
This paper argues that some of the ideas of connectionism are not only logically flawed, but that they are also inconsistent with some commonly observed human learning behavior. In addition, this paper attempts to define some common, externally observed, properties of the human learning process, properties that are common to all types of human learning. It is expected that any theory of learning should account for these common properties. Characterization of an autonomous learning system such as the brain has been one of the “large” missing pieces in connectionism and other brain-related sciences. The external characteristics of learning algorithms have never been defined in these fields. They largely pursued algorithm development from an “internal mechanisms” point of view. This paper is an attempt to rectify that situation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Roy, A. (2002). On Neural Networks, Connectionism and Brain-Like Learning. In: Apolloni, B., Kurfess, F. (eds) From Synapses to Rules. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0705-5_16
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0705-5_16
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5204-4
Online ISBN: 978-1-4615-0705-5
eBook Packages: Springer Book Archive