Building and Improving Artificial Neural Network Classifier
Sanghita Saha1, Ramanathan.L2

1Sanghita Saha, SCOPE, VIT, Vellore, (Tamil Nadu), India.
2Ramanathan.L, SCOPE, VIT, Vellore, (Tamil Nadu), India.

Manuscript received on 30 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 2742-2747 | Volume-8 Issue-9, July 2019 | Retrieval Number: I8311078919/19©BEIESP | DOI: 10.35940/ijitee.I8311.078919
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: Deep learning is a spectrum of machine learning which uses advanced neural networks to solve the various machine learning problems. Its working is very similar to the working of a human brain where the models take decision based on various input parameters. There are multiple open source libraries which implement neural networks, like Tensorflow, Theano, PyTorch, Keras etc. In this paper we have proposed a generic architecture that can be used for any type of classification problems with binary output or classification output using Deep Learning model: Artificial Neural Network (ANN). In the architectural model after Data preprocessing we first build the ANN classifier using Keras library with Tensorflow backends, second step we have apply Cross-validation method for better accuracy. Then we perform Dropout Regularization method for preventing from overfitting and at last we have applied grid search technique for parameter tuning that basically will test several combinations of Hyperparameter values and will eventually return the best selection choice with K-Fold cross validation. And the experimental results shows in higher accuracy with ours proposed architecture and in our proposed architecture results we remove the randomness from the model. In the proposed architecture we can again rebuild developing our model using Keras Callback function by using this feature in our model it does not create any major difference in terms of accuracy. But as we know the accuracy will vary with parameter tuning. The main advantage of using Keras Callback function method is it’s saves a lot of time for building model and it is easy for debugging the model.
Keywords: Deep Learning, Keras, Tensorflow, ANN, Callback function.

Scope of the Article: Deep learning