An All-Batch Loss for Constructing Prediction Intervals
Source abstract
Abstract
The prediction interval (PI) is an important research topic in reliability analyses and decision support systems. Data size and computation costs are two of the issues which may hamper the construction of PIs. This paper proposes an all-batch (AB) loss function for constructing high quality PIs. Taking the full advantage of the likelihood principle, the proposed loss makes it possible to train PI generation models using the gradient descent (GD) method for both small and large batches of samples. With the structure of dual feedforward neural networks (FNNs), a high-quality PI generation framework is introduced, which can be adapted to a variety of problems including regression analysis. Numerical experiments were conducted on the benchmark datasets; the results show that higher-quality PIs were achieved using the proposed scheme. Its reliability and stability were also verified in comparison with various state-of-the-art PI construction methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Non-Destructive Testing Techniques · Machine Learning and ELM
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
Funding
National Key Research and Development Program of China
References (44)
Show source-provided references
1. Prediction intervals for growth curve forecasts10.1002/for.3980140502 ↗
2. Shen, Y., Wang, X., and Chen, J. (2018). Wind power forecasting using multi-objective evolutionary algorithms for wavelet neural network optimized prediction intervals. Appl. Sci., 8.10.3390/app8020185 ↗
3. Chance constrained extreme learning machine for nonparametric prediction intervals of wind power generation10.1109/TPWRS.2020.2986282 ↗
4. Probabilistic forecast of wind power generation with data processing and numerical weather predictions10.1109/TIA.2020.3037264 ↗
5. Mykhailovych, T., and Fryz, M. (2020, January 25–29). Model and information technology for hourly water consumption interval forecasting. Proceedings of the IEEE 15th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, Lviv-Slavske, Ukraine.10.1109/TCSET49122.2020.235452 ↗
6. Operating mode recognition based on fluctuation interval prediction for iron ore sintering process10.1109/TMECH.2020.2992706 ↗
7. Short-term parking demand prediction method based on variable prediction interval10.1109/ACCESS.2020.2976433 ↗
8. Cheng, J., Duan, D., Cheng, X., Yang, L., and Cui, S. (2021). Adaptive control for energy exchange with probabilistic interval predictors in isolated microgrids. Energies, 14.10.3390/en14020375 ↗
9. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
10. Confidence interval prediction for neural network models10.1109/72.478409 ↗
11. Prediction intervals for artificial neural networks10.1080/01621459.1997.10474027 ↗
12. Bishop, C.M. (1995). Neural Networks for Pattern Recognition, Oxford University Press.10.1093/oso/9780198538493.001.0001 ↗
13. The evidence framework applied to classification networks10.1162/neco.1992.4.5.720 ↗
14. Heskes, T. (1997). Practical confidence and prediction intervals. Proceedings of the 1997 Conference on Advance in Neural Information Processing Systems, MIT Press.
15. Carney, J.G., Cunningham, P., and Bhagwan, U. (1999, January 10–16). Confidence and prediction intervals for neural network ensembles. Proceedings of the International Joint Conference on Neural Networks, Washington, DC, USA.
16. Errouissi, R., Cárdenas-Barrera, J.L., Meng, J., and Guerra, E.C. (2015, January 20–24). Bootstrap prediction interval estimation for wind speed forecasting. Proceedings of the IEEE Energy Conversion Congress and Exposition, Montreal, QC, Canada.10.1109/ECCE.2015.7309931 ↗
17. Mancini, T., Pardo, H.C., and Olmo, J. (2020). Prediction intervals for deep neural networks. arXiv.
18. Dybowski, R., and Roberts, S.J. (2001). Confidence Intervals and Prediction Intervals for Feed-Forward Neural Networks, Cambridge University Press.10.1017/CBO9780511543494.013 ↗
19. Nix, D.A., and Weigend, A.S. (July, January 28). Estimating the mean and variance of the target probability distribution. Proceedings of the IEEE International Conference on Neural Networks, Orlando, FL, USA.
20. Lower upper bound estimation method for construction of neural network-based prediction intervals10.1109/TNN.2010.2096824 ↗
21. Ak, R., Li, Y.-F., Vitelli, V., and Zio, E. (2013). Multi-Objective Genetic Algorithm Optimization of a Neural Network for Estimating Wind Speed Prediction Intervals, HAL. Unpublished work.
22. Wind power interval prediction based on improved PSO and BP neural network10.5370/JEET.2017.12.3.989 ↗
23. Long, H., Zhang, C., Geng, R., Wu, Z., and Gu, W. (2021). A combination interval prediction model based on biased convex cost function and auto rncoder in solar power prediction. IEEE Trans. Sustain. Energy.10.1109/TSTE.2021.3054125 ↗
24. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
25. Pearce, T., Zaki, M., Brintrup, A.M., and Neely, A. (2018, January 10–15). High-quality prediction intervals for deep learning: A distribution-free, ensembled approach. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden.
26. Hoffer, E., Hubara, I., and Soudry, D. (2017, January 4–9). Train longer, generalize better: Closing the generalization gap in large batch training of neural networks. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
27. A network framework for small-sample learning10.1109/TNNLS.2019.2951803 ↗
28. Salem, T.S., Langseth, H., and Ramampiaro, H. (2020). Prediction intervals: Split normal mixture from quality-driven deep ensemble. arXiv.
29. Comprehensive review of neural network-based prediction intervals and new advances10.1109/TNN.2011.2162110 ↗
30. A prediction interval based approach to determine optimal structures of neural network metamodels10.1016/j.eswa.2009.07.059 ↗
31. Machine learning approaches for estimation of prediction interval for the model output10.1016/j.neunet.2006.01.012 ↗
32. Laarhoven, P.J.M.V., and Aarts, E.H.L. (1987). Simulated Annealing: Theory and Applications, Kluwer.
33. Hedonic housing prices and the demand for clean air10.1016/0095-0696(78)90006-2 ↗
34. Modeling of strength of high-performance concrete using artificial neural networks10.1016/S0008-8846(98)00165-3 ↗
35. Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools10.1016/j.enbuild.2012.03.003 ↗
36. A robotics toolbox for MATLAB10.1109/100.486658 ↗
37. Machine learning approaches for improving condition-based maintenance of naval propulsion plants
38. Real-time simulation of a cogag naval ship propulsion system
39. Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods10.1016/j.ijepes.2014.02.027 ↗
40. Kaya, H., Tüfekci, P., and Gürgen, S.F. (2012, January 24–25). Local and hlobal learning methods for predicting power of a xombined gas & steam turbine. Proceedings of the International Conference on Emerging Trends in Computer and Electronics Engineering, Dubai, United Arab Emirates.
41. Modeling wine preferences by data mining from physicochemical properties10.1016/j.dss.2009.05.016 ↗
42. Geometry, resistance and stability of the Delft systematic yacht hull series110.3233/ISP-1981-2832801 ↗
43. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
44. Efficient estimation of flood forecast prediction intervals via single and multi-objective versions of the LUBE method10.1002/hyp.10799 ↗