Analysis of Deep Learning Models using Convolution Neural Network Techniques
N.Durai Murugan1, SP.Chokkalingam2, Samir Brahim Belhaouari3
1N.Durai Murugan, Research Scholar, Assistant Professor, Department of CSE, Saveetha Institute of Medical and Technical Sciences, Rajalakshmi Engineering College, Chennai (Tamil Nadu), India.
2SP.Chokkalingam, Professor, Department of CSE, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai (Tamil Nadu), India.
3Samir Brahim Belhaouari, Associate Professor, College of Science and Engineering, Hamad Bin Khalifa University, Qatar, College of Science, Alfaisal University.
Manuscript received on 29 May 2019 | Revised Manuscript received on 11 June 2019 | Manuscript Published on 22 June 2019 | PP: 568-573 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C11220283S19/19©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 (

Abstract: Deep Learning is the one of the souls of Artificial Intelligence and it is rapid growing in the medical data analysis research field, in many conditions Deep learning models are look like the neurons in brain, although both contain enormous number of computation Neurons units also called neurons that are not extremely intelligent in separation but improve optimistically when they interact with each other. The key objective is that many Convolution Neural Network models are available for image analysis which gives different accuracy in different aspects by training the model. A major analysis of Convolution models using Multilayer Perceptron is driven to analyses the image dataset of handwritten digits and to experiment by variations that are occurred in during the various changes that applied to the Convolution techniques like padding, stride and pooling to get best models in terms of the best accuracy and time optimization by minimizing the loss function.
Keywords: Convolution Neural Network, Multilayer Perceptron, Deep learning, Deep Neural Network, Activation Function.
Scope of the Article: Deep Learning