An evaluation of the capacity of a machine or system to functionally survive the breakdown or impairment of some of its parts.
In parallel or neural networks and generally in complex systems, the breakdown of some elements or some unexpected inputs do not usually inhibits seriously the system's capacities, or limits only slightly its operative power. This is because computing or operation is distributed in the whole of the parallel network, which is considerably redundant.
However, when disabled, the network must undergo a reorganizing process, in order to create new internal connections to replace those which have been destroyed. A good example is the reconstruction of physical abilities and knowledge in persons which have been affected by a not overly destructive cerebral haemorrhage.
The subject of global realibility in neural computation based on unreliable components has been first considered by J.von NEUMANN (1956).
- 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: