Optimizing Connection Weights in a Long Short-Term Memory (LSTM) Using Whale Optimization Algorithm (WOA): A Review

Abuzairu Ahmad, Kabiru Ibrahim Musa, Fatima Umar Zambuk, Mustapha Abdulrahman Lawal

Abstract


Many academics have recently developed an interest in the learning process of long short-term memory, which is widely accepted as one of the trickiest issues in machine learning. The main challenges of the standard training procedure are usually local optima stagnation and slow convergence. As a result, the whale optimization algorithm can be used to solve long short-term memory local minima. Optimizing connection weights can go a long way toward assisting the authority to properly addressing network problems. A review of the related literatures for optimization weights has been conducted in this paper with the sole purpose of identifying a gap for future research. A keyword search was conducted to locate relevant literatures from various academic databases, and the papers gathered were reviewed to determine their areas of strength and weakness. The term "independent" refers to a person who does not work for the government.

Full Text:

PDF

References


Aljarah, I., Faris, H., & Mirjalili, S. (2018).Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Computing, 22(1), 1-15.

Chui,K. T., Gupta, B. B., & Vasant, P. (2021). A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine.Electronics, 10(3), 285.

ElSaid, A., Jamiy, F. E., Higgins, J., Wild, B., & Desell, T. (2018, July).Using ant colony optimization to optimize long short-term memory recurrent neural networks. In Proceedings of the Genetic and Evolutionary Computation Conference (pp. 13-20).

ElSaid, A., Karns, J., Ororbia II, A., Krutz, D., Lyu, Z., & Desell, T. (2020). Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation. arXiv preprint arXiv:2006.02655.

Gao, Y., Chen, K., Gao, H., Zheng, H., Wang, L., & Xiao, P. (2020). Energy consumption prediction for 3-RRR PPM through combining LSTM neural network with whale optimization algorithm. Mathematical Problems in Engineering, 2020.

Lei, Y., Li, N., Gontarz, S., Lin, J., Radkowski, S., & Dybala, J. (2019). A model-based method for remaining useful lif e prediction of machinery. IEEE Transactions on reliability, 65(3), 1314-1326.

Liu, Z. H., Meng, X. D., Wei, H. L., Chen, L., Lu, B. L., Wang, Z. H., & Chen, L. (2021). A regularized LSTM method for predicting remaining useful life of rolling bearings. International Journal of Automation and Computing, 18(4), 581-593.

Ngarambe, J., Irakoze, A., Yun, G. Y., & Kim, G. (2020). Comparative performance of machine learning algorithms in the prediction of indoor daylight illuminances. Sustainability,12(11), 4471.

Salman, A. G., Heryadi, Y., Abdurahman, E., & Suparta, W. (2018). Single layer & multi-layer long short-term memory (LSTM) model with intermediate variables for weather forecasting. Procedia Computer Science, 135, 89-98.

Siami-Namini, S., & Namin, A. S. (2018). Forecasting economics and financial time series: ARIMA vs. LSTM. arXiv preprint arXiv:1803.06386.

Yadav, A., Jha, C. K., & Sharan, A. (2020). Optimizing LSTM for time series prediction in Indian stock market. Procedia Computer Science, 167, 2091-2100.

Yuliyono, A. D., & Girsang, A. S. (2019). Artificial bee colony-optimized LSTM for bitcoin price prediction. Advances in Science, Technology and Engineering Systems Journal, 4(5), 375-383.


Refbacks

  • There are currently no refbacks.