Abstract:Long Short-Term Memory (LSTM) neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem of model selection, including hyperparameter tuning, architecture specification, and regularization choice remains largely heuristic and computationally expensive. In this paper, we propose a unified statistical framework for systematic model selection in LSTM networks. Our framework extends classical model selection ideas, such as information criteria and shrinkage estimation, to sequential neural networks. We define penalized likelihoods adapted to temporal structures, propose a generalized threshold approach for hidden state dynamics, and provide efficient estimation strategies using variational Bayes and approximate marginal likelihood methods. Several biomedical data centric examples demonstrate the flexibility and improved performance of the proposed framework.
| Subjects: | Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Applications (stat.AP); Other Statistics (stat.OT) |
| MSC classes: | 62M10, 92B20, 62P10, 62P99 |
| Cite as: | arXiv:2506.06840 [stat.ML] |
| (or arXiv:2506.06840v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2506.06840 arXiv-issued DOI via DataCite |
From: Fahad Mostafa [view email]
[v1]
Sat, 7 Jun 2025 15:44:27 UTC (760 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。