- 期刊
- OpenAccess
A Novel Strategy for Speed up Training for Back Propagation Algorithm via Dynamic Adaptive the Weight Training in Artificial Neural Network
並列摘要
The drawback of the Back Propagation (BP) algorithm is slow training and easily convergence to the local minimum and suffers from saturation training. To overcome those problems, we created a new dynamic function for each training rate and momentum term. In this study, we presented the (BPDRM) algorithm, which training with dynamic training rate and momentum term. Also in this study, a new strategy is proposed, which consists of multiple steps to avoid inflation in the gross weight when adding each training rate and momentum term as a dynamic function. In this proposed strategy, fitting is done by making a relationship between the dynamic training rate and the dynamic momentum. As a result, this study placed an implicit dynamic momentum term in the dynamic training rate. This α_(dmic) = f(1/η_(dmic)). This procedure kept the weights as moderate as possible (not to small or too large). The 2-dimensional XOR problem and buba data were used as benchmarks for testing the effects of the 'new strategy'. All experiments were performed on Matlab software (2012a). From the experiment's results, it is evident that the dynamic BPDRM algorithm provides a superior performance in terms of training and it provides faster training compared to the (BP) algorithm at same limited error.
延伸閱讀
- Liu, L. C. (2019). Developing Artificial Neural Network based Non-linear Classifiers with Complexity Reduction Methods for High Speed Optical Transmission Systems [master's thesis, National Chiao Tung University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0030-0306202016341678
- Si, L., Liu, X. H., Tan, C., & Wang, Z. B. (2014). A Novel Classification Approach through Integration of Rough Sets and Back-Propagation Neural Network. Journal of Applied Mathematics, 2014(), 712-722-773. https://doi.org/10.1155/2014/797432
- Devi, R. M., & Kuppuswami, S. (2016). CAST: A constant Adaptive Skipping Training Algorithm for Improving the Learning Rate of Multilayer Feedforward Neural Networks. Research Journal of Applied Sciences, Engineering and Technology, 12(8), 790-812. https://doi.org/10.19026/rjaset.12.2780
- 黃子豪（2019）。Using Back Propagation Neural Network to Enhance Accuracy of Demanding Forecasting Among Multiple Factor Influences–In The Case of Internet Retail〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201900641
- Chang, Y. T., Lin, J., Shieh, J. S., & Abbod, M. (2012). Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction. Advances in Fuzzy Systems, 2012(), 482-490. https://doi.org/10.1155/2012/951247