
We suggest a description of thermodynamical systems, focusing on near-to-equilibrium states of the systems, within the structure of random graphs to map them to neural nets. We then use the component subgraph configurations of the random graphs that are the stationary states of the near-to-equilibrium systems to represent concepts in an unstructured form. This enables the evolution property of random graphs to give temporal sequences of concepts. Such sequences can be interconnected to form an expert system for processing unstructured data. © 1994 John Wiley & Sons, Inc.
Neural nets applied to problems in time-dependent statistical mechanics, Learning and adaptive systems in artificial intelligence, Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence
Neural nets applied to problems in time-dependent statistical mechanics, Learning and adaptive systems in artificial intelligence, Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 1 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
