Abstract | ||
---|---|---|
The studies addressed in this paper refer to the following: (i)Deducing a functional relationship between the logistic output versus input values in a neural network when the boundaries of the input and output sets are fuzzy and developing a fuzzy Riccardi differential equation (FRDE) which governs the relevant nonlinear process(es) associated with the neural complex. (ii)Evolving the dynamics of learning associated with a fuzzy neural network in terms of a fuzzy uncertainty parameter via a fuzzy Fokker–Planck equation (FFPE). The logistic growth of output versus input in the fuzzy neural complex as dictated by the FRDE, follows not only a generalized representation of a stochastically justifiable sigmoidal function (as decided by the spatial long-range order of neuronal state proliferation across the network), but it also captures the approximate nature of reasoning and perception associated with the “granular information” vis-á-vis the fuzzy set(s) of the variables involved. As regards to the solution of FRDE, it represents the function approximation of overlapping output clusters resulting from the segments of input-space grouped into membership classes (each depicting a certain range of input values). An architecture based on the fuzzy sigmoidal description of the nonlinear process(es) involved is presented and discussed. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1016/S0925-2312(98)00006-X | Neurocomputing |
Keywords | Field | DocType |
Fuzzy,Nonlinear activity function,Fuzzy sigmoid,Fuzzy neural dynamics | Neuro-fuzzy,Defuzzification,Fuzzy classification,Fuzzy set operations,Fuzzy logic,Fuzzy mathematics,Artificial intelligence,Fuzzy number,Membership function,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 1-3 | 0925-2312 |
Citations | PageRank | References |
0 | 0.34 | 18 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Perambur S. Neelakanta | 1 | 27 | 10.35 |
Salahalddin T. Abusalah | 2 | 0 | 1.69 |
Dolores F. De Groff | 3 | 8 | 3.26 |
Joseph S. Park | 4 | 4 | 3.87 |