Open Access Open Access  Restricted Access Subscription or Fee Access

Generalised Neural Network

Sunil Kumar Kashyap, Deepshikha Sharma

Abstract


The neural network is generalised in this paper. The resultant becomes more feasible than earlier. The applicability of the proposed is discussed in this paper also. The new characteristics found in the neural network. The probabilistic study based neural network is performed in this paper. The composition of discrete and continuous probability performed for generalising the neural network in this paper. An efficient neural network performance is presented in this paper by using this composition. The computational complexity lies with this composition provides the security at high level. The feasibility of the neural network comprises with the optimized computational complexity.

Full Text:

PDF

References


G.V. Cybenko. Approximation by Superpositions of a Sigmoidal function, Math Control Signals Syst. 1989; 2: 303–14p.

H.K.D.H. Bhadeshia. neural networks in materials science (PDF), ISIJ Int. 1999; 39(10): 966–79p.

S. Lyons. Changes in cell shape are correlated with metastatic potential in murine, Biol Open. 2016; 5(3): 289–9p.

A. Einstein. Uber die yom relativitatsprinzip geforderte tragheit der Energie, Ann Phys. 328(7): 371–84p.

G.S. Ohm. Die galvanische Kette: Mathematisch Bearbeitet. Reimann, 181, 1827.




DOI: https://doi.org/10.37628/ijece.v3i2.697

Refbacks

  • There are currently no refbacks.