"A system that contains no explicit symbols or rules" (J. SUTHERLAND, 1995, p.64).
The commonest kind "are known as neural nets" "They consist of layers of units, each layer connected to the rest at random. The first layer is triggered by an input and the last layer represents output. The intermediate layer or layers are called "hidden units". The connections between layers are triggered in parallel, and their strengths increased or decreased with succesive inputs" (Ibid).
Two basic characteristics of connectionist systems are that:
- they construct their own rules according to succesive responses to succesive inputs.
- they are not totally impaired when locally damaged, but only slightly deteriorated.
The brain seems to be a connectionist system.
- 1) General information
- 2) Methodology or model
- 3) Epistemology, ontology and semantics
- 4) Human sciences
- 5) Discipline oriented
To cite this page, please use the following information:
Bertalanffy Center for the Study of Systems Science (2020). Title of the entry. In Charles François (Ed.), International Encyclopedia of Systems and Cybernetics (2). Retrieved from www.systemspedia.org/[full/url]
We thank the following partners for making the open access of this volume possible: