Back Propagation Neural Network(BPNN) and Sigmoid Activation Function in Multi-Layer Networks

Authors

  • Renas Rajab Asaad Department of Computer Science, Nawroz University, Duhok, Kurdistan Region - Iraq
  • Rasan Ismail Ali Department of Computer Science, Nawroz University, Duhok, Kurdistan Region - Iraq

DOI:

https://doi.org/10.25007/ajnu.v8n4a464

Keywords:

Artificial Neural networks, Sigmoid Function, Backpropagation ANNs, Neural networks

Abstract

Back propagation neural network are known for computing the problems that cannot easily be computed (huge datasets analysis or training) in artificial neural networks. The main idea of this paper is to implement XOR logic gate by ANNs using back propagation neural network for back propagation of errors, and sigmoid activation function. This neural network to map non-linear threshold gate. The non-linear used to classify binary inputs (x1, x2) and passing it through hidden layer for computing coefficient_errors and gradient_errors (Cerrors, Gerrors), after computing errors by (ei = Output_desired- Output_actual) the weights and thetas (ΔWji = (α)(Xj)(gi), Δϴj = (α)(-1)(gi)) are changing according to errors. Sigmoid activation function is = sig(x)=1/(1+e-x) and Derivation of sigmoid is = dsig(x) = sig(x)(1-sig(x)). The sig(x) and Dsig(x) is between 1 to 0.

 

Downloads

Download data is not yet available.

References

[1] Jacobson, L. (2013). Introduction to Artificial Neural networks.
[2] Da Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H. B., & dos Reis Alves, S. F. (2017). Artificial neural networks. Cham: Springer International Publishing.
[3] Alan P. O. et al (). Adaptive Boolean Logic Using Ferroelectrics Capacitors as Basic Units of Artificial Neurons. www.electronic-tutorials.ws. [Accessed Date: Nov 2019].
[4] Sibi, P., S. Allwyn Jones, and P. Siddarth. (2013). "Analysis of different activation functions using back propagation neural networks." Journal of Theoretical and Applied Information Technology 47.3: 1264-1268.
[5] Li, H., Zhang, Z., & Liu, Z. (2017). Application of artificial neural networks for catalysis: a review. Catalysts, 7(10), 306.
[6] haq Shaik, E., & Rangaswamy, N. (2017). Multi-mode interference-based photonic crystal logic gates with simple structure and improved contrast ratio. Photonic Network Communications, 34(1), 140-148.
[7] Wanto, A., Windarto, A. P., Hartama, D., & Parlina, I. (2017). Use of Binary Sigmoid Function And Linear Identity In Artificial Neural networks For Forecasting Population Density. International Journal Of Information System & Technology, 1(1), 43-54.
[8] Chung, H., Lee, S. J., & Park, J. G. (2016, July). Deep neural networks using trainable activation functions. In 2016 International Joint Conference on Neural networks (IJCNN) (pp. 348-352). IEEE.
[9] Bhattacherjee, A., Roy, S., Paul, S., Roy, P., Kausar, N., & Dey, N. (2020). Classification approach for breast cancer detection using back propagation neural networks: a study. In Deep Learning and Neural networks: Concepts, Methodologies, Tools, and Applications (pp. 1410-1421). IGI Global.

Published

2019-11-20

How to Cite

Asaad, R. R., & Ali, R. I. (2019). Back Propagation Neural Network(BPNN) and Sigmoid Activation Function in Multi-Layer Networks. Academic Journal of Nawroz University, 8(4), 216–221. https://doi.org/10.25007/ajnu.v8n4a464

Issue

Section

Articles