Multi-layer Neural Network Perception for Large Data Prediction using R Programming
Abstract
This review article primarily focus on neural network perceptionitechniques for large data analysis using r programming on secondary data set. Although there is a large confusion while selctioning an appropriate analysis tools for the newer researchersr when there was a large set of associative variables like CTG data sets having 2126 observations in 22 attributing variables of numeric types. The last variable NSP with categorical type 1,2 and 3 stores best, mediam and least properties. This article attempts to explore the detail analysis using the concept of multi-ilayered neural networks procedures for sample CTG data sets where each step to reach conclusion were sufficiently explained. Its purpose is to explain the simplest form of analysis when researcher meets large number of dependent and independent varialbes research data structure using software R whose results are summarized and inferenced with sufficiently with interemediate results and conclusions were drawn using appropriate graphical interpretation were analyze using 8 hidden layers with activation of relu of 21 independent variables and loss is calculated with different epoch of categorical crossentropy . The each model value is evaluated with confusion matrixed prediction. The model is considered as best fit when the two-line graphs were in constant in more iterations. The tenser flow package is widely used in image recognition, computer vision, speech / sound recognition and time series analysis and many more.
References
Bouziane, A. (2018). Neural network analysis.
Bruke, j. (2017). Big data analysis using neural networks.
Gurney, K. (2004). An introduction to Neural Network. UCL Press Limited is an imprint of the Taylor & Francis Grou.
Haluk Demirkan, C. B. (2015). Innovations with Smart Service Systems: Analytics, Big Data, Cognitive Assistance, and the Internet of Everything.
Johnson, S. a. (2004). Neural Coding Strategies and Mechanisms of Competition. Cognitive Syatems Research.
Lim, S. (2018). Adaptive Learning Rule for Hardware based Deep Neural Networks.
McAteer, M. (2018). An introduction to probabilistic programming, now available in TensorFlow Probability.
Noon, H. (2013). Artificial Neural Network : Beginning of the AI revolution.
Rouse, M. (2018). Big_data_analysis_using_neural_networks.
Saxena, S. (2018). Becoming Human: Artificial Intelligence Magazine.
Shwe, M. (2018). An introduction to probabilistic programming, now available in TensorFlow Probability. Retrieved from https://medium.com/tensorflow/an-introduction-to-probabilistic-programming-now-available-in-tensorflow-probability-6dcc003ca29e?fbclid=IwAR2tP68gZEXfGBs_Q5vYVZUZxICcv8nRkvpkn8n3AsHN2ZlRglij55ngSzw
Stephen Notley, M. M.-I. (2018). Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers.
Zhang, Y. (2017). Big data analysis using neural networks.