Constructive Neural Network: A Framework
Jaswinder Kaur1, Neha Gupta2
1Jaswinder Kaur, School of Engineering & Technology, Ansal University, Gurgaon, India.
2Neha Gupta, School of Engineering & Technology, Ansal University, Gurgaon, India.
Manuscript received on November 26, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 5321-5324 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3304129219/2019©BEIESP | DOI: 10.35940/ijeat.B3304.129219
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In this paper, two techniques for construction of feedforward neural network are being reviewed: pruning neural network algorithms and constructive neural network algorithms. In pruning method, training starts with a larger than required network and subsequently delete the redundant hidden nodes and redundant weights till there is a satisfactory solution. In the constructive method, training of the network starts with minimum structure and then according to some predefined rule some more layers of neurons are added. A number of major issues are discussed that can be considered while constructing a constructive neural network i.e. how to select network architecture, network growing strategy, weight freezing, optimization technique, activation function and stoppage criteria.
Keywords: Neural networks, Pruning algorithm, Constructive algorithm, Optimization technique and Activation function.