Improved Time Training with Accuracy of Batch Back Propagation Algorithm Via Dynamic Learning Rate and Dynamic Momentum Factor

The man problem of batch back propagation (BBP) algorithm is slow training and there are several parameters needs to be adjusted manually, also suffers from saturation training. The learning rate and momentum factor are significant parameters for increasing the efficiency of the (BBP). In this study, we created a new dynamic function of each learning rate and momentum facor. We present the DBBPLM algorithm, which trains with a dynamic function for each the learning rate and momentum factor. A Sigmoid function used as activation function. The XOR problem, balance, breast cancer and iris dataset were used as benchmarks for testing the effects of the dynamic DBBPLM algorithm. All the experiments were performed on Matlab 2012 a. The stop training was determined ten power -5. From the experimental results, the DBBPLM algorithm provides superior performance in terms of training, and faster training with higher accuracy compared to the BBP algorithm and with existing works.

[1]  Zhong Li,et al.  A classifier of satellite signals based on the back-propagation neural network , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[2]  Mohammad Shukri Salman,et al.  Back-propagation algorithm with variable adaptive momentum , 2016, Knowl. Based Syst..

[3]  Fatma Susilawati Mohamad,et al.  A Review on Enhancements to Speed up Training of the Batch Back Propagation Algorithm , 2016 .

[4]  Pengfei Huang,et al.  An improved back propagation neural network prediction model for subsurface drip irrigation system , 2017, Comput. Electr. Eng..

[5]  R. Karthikeyan,et al.  Multi Layer Perception Type Artificial Neural Network based Traffic Control , 2016 .

[6]  Sanei Saeid,et al.  Improving the Neural Network Training for Face Recognition using Adaptive Learning Rate, Resilient Back Propagation and Conjugate Gradient Algorithm , 2011 .

[7]  Hamid Soltanian-Zadeh,et al.  Fast opposite weight learning rules with application in breast cancer diagnosis , 2013, Comput. Biol. Medicine.

[8]  Jian-Huai Cai,et al.  A kind of BP neural network algorithm based on grey interval , 2011, Int. J. Syst. Sci..

[9]  Yiqiu Fang,et al.  An new back propagation algorithm with chaotic learning rate , 2010, 2010 IEEE International Conference on Software Engineering and Service Sciences.

[10]  Nazri Mohd Nawi,et al.  Enhancing Back Propagation Neural Network Algorithm with Adaptive Gain on Classification Problems , 2011 .

[11]  R. Kalaivani,et al.  Neural Network based Vibration Control for Vehicle Active Suspension System , 2016 .

[12]  Zhao Peng,et al.  Improvements of coefficient learning in BPNN for image restoration , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[13]  Vishnu Pratap Singh Kirar.  Improving the Performance of Back-Propagation Training Algorithm by Using ANN , 2015 .

[14]  Ke Xiao,et al.  BP neural network-based web service selection algorithm in the smart distribution grid , 2014, The 16th Asia-Pacific Network Operations and Management Symposium.

[15]  Hamed Azami,et al.  A comparative study of breast cancer diagnosis based on neural network ensemble via improved training algorithms , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  Jun Wang,et al.  Exponent back propagation neural network forecasting for financial cross-correlation relationship , 2016, Expert Syst. Appl..