Abstract
This paper argues that some of the ideas of connectionism are not only logically flawed, but that they are also not consistent with some commonly observed human learning processes and 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. The paper also suggests a new paradigm for the internal mechanisms of the brain, one that can overcome the limitations of classical connectionist learning. It is argued in the paper, both from a logical point of view and on the basis of some recent neurobiological findings, that one or more substructures in the brain control other substructures. Thus the paper proposes a control theoretic approach to understanding how the brain works and learns.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the International Joint Conference on Neural Networks |
Place of Publication | United States |
Publisher | IEEE |
Pages | 74-79 |
Number of pages | 6 |
Volume | 1 |
State | Published - 1999 |
Event | International Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA Duration: Jul 10 1999 → Jul 16 1999 |
Other
Other | International Joint Conference on Neural Networks (IJCNN'99) |
---|---|
City | Washington, DC, USA |
Period | 7/10/99 → 7/16/99 |
ASJC Scopus subject areas
- Software