Hybrid Neural Network with Modified Cuckoo Search via Cluster Technique
1Dr. K.Thinakaran, Department of CSE, Saveetha School of Engineering, SIMATS Chennai (Tamil Nadu), India.
2Dr. K. Santhi, Department of CSE, Saveetha School of Engineering, SIMATS Chennai (Tamil Nadu), India.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 1894-1898 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7906068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Levenberg-Marquardt again-spread estimation, as a Feed forward Neural Network (FNN) arranging framework, has numerous impediments associated with over fitting and close to to perfect problems .This paper proposed every other meta-heuristic pursue calculation, in light of cuckoo winged animal’s on the spot to put together lower back augmentation in conducting expedient get together fee and to sidestep community minima issue. The proposed modified Cuckoo Search Back-Propagation (MCSBP) is separated and PSO-BP estimation, and other cream assortments. The consequences exhibit that the ability of BP making ready technique is updated while united with the Cuckoo search approach.
Keywords: Lower Back Inflicting Neural Gadget, Cuckoo Seek Tally, Cluster Technique, Near-By Way Of Minima, PSO, Levenberg-Marquardt.
Scope of the Article: Computer Networking