Inversion ofcomplex Neural Network
Manmohan Shukla1, B. K. Tripathi2
1Manmohan Shukla, Department of Computer Science and Engineering, PSIT Kanpur (U.P), India.
2Marion Sinclair, Department of Science and Engineering, HBTU Kanpur (U.P), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 13 February 2019 | Manuscript published on 28 February 2019 | PP: 638-641 | Volume-8 Issue-4, February 2019 | Retrieval Number: D2874028419/19©BEIESP
Open Access | Editorial and Publishing 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: This paper presents a novel application of complex neural network which has been modeled by the implementation of gradient descent inversion algorithm in complex domain. The methods reported prior to this work were limited to real domain only. By the learning of function mapping in complex domain, the performance of neural network has been analyzed. An improved performance of complex neural network has resulted in the development of a Novel Complex Neuron Model.
Keyword: Inversion, Complex-Valued Neural Network, Gradient Descent Search And Activation Function.
Scope of the Article: Neural Information Processing