Deep learning has been playing a crucial role in making applications much smarter than before and more reliable. The reliability of a model can be marked out using parameters like accuracy. Recurrent Neural Networks, is a complicated deep learning model, which can be hard to develop but can be more reliable if properly trained. A good collection of data alone cannot give good accuracies. Fuzzy Logic is a statistical approach that can be used to mold the data based on the degree of truth. Gini index based fuzzification is a technique that builds the data by finding relations within the data and then fuzzifying it. In this paper, the gini index based fuzzification is applied on the data set and this fuzzified data is used in training and testing the RNN model. Here, better Accuracy is observed for RNN model with fuzzy data compared to the actual data.

Deep Learning, Recurrent Neural Networks, RNN, Fuzzy logic, Gini Index

[1] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, And A. Torralba, “Learning Deep Features For Discriminative Localization,” In Proceedings Of The Ieee Conference On Computer Vision And Pattern Recognition , Pp. 2921–2929, 2016
[2] Jürgen Schmidhuber, Deep Learning in neural networks: An Overview, Elsevier(Neural networks), vol 61, p 85-117, 2015
[3] Anirban Sarkar, Aditya Chattopadhyay, Prantik Howlader, V. Balasubramanian, Grad-Cam++: “Generalized Gradient-Based Visual Explanations For Deep Convolutional Networks”, Proceedings Of Ieee Winter Conference On Applications Of Computer Vision (Wacv`18), Mar 2018. [Arxiv].
[4] Bing Cheng, D.M.Titterington, Neural Networks: A Review from a Statistical Perspective.
[5] Yann LeCun, Yoshua Bengio & Geoffrey Hinton, Deep learning,Nature volume 521, pages 436–444 (28 May 2015)
[6] Michael Hüsken, Peter Stagge Recurrent neural networks for time series classification, Neurocomputing Volume 50, Pages 223-235,January 2003
[7] Yuan, Y., & Michael, J. S. (1995). Induction of fuzzy decision trees. Fuzzy Sets and Systems, 69, 125–139.
[8] Cristina, O., & Wehenkel, L. (2003). A complete fuzzy decision tree technique. Fuzzy Sets and Systems, 138, 221–254
[9] Ching-Hsue Cheng, Jing-RongChang, Che-AnYeha, Entropy-based and trapezoid fuzzification-based fuzzy time series approaches for forecasting IT project cost, Technological Forecasting and Social Change Volume 73, Issue 5, June 2006, Pages 524-542
[10] Clarence W. de Silva, Fundamentals of Fuzzy Logic, Intelligent Control
[11] M Anidha1, K Premalatha, An application of fuzzy normalization in miRNA data for novel feature selection in cancer classification, Biomedical Research 2017; 28 (9): 4187-4195
[12] B.chandra, P.Paul Varghese, fuzzifying gini index based decision trees, Elsevier ( Expert systems with applications 36 (2009), pp 8549 - 8559.
[13] S.V.G.Reddy, K.Thammi Reddy, V.Valli Kumari, Enhancing the Speed, Accuracy of Deep Learning Classifier using Gini index based Fuzzy decision trees
[14] Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models. Luis M. Candanedo, Véronique Feldheim. Energy and Buildings. Volume 112, 15 January 2016, Pages 28-39.
[15] Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng, Google Brain, TensorFlow: A System for Large-Scale Machine Learning.