统一实现多种RNN模型，提升可复现性与开发效率。
Unified Implementations of Recurrent Neural Networks in Multiple Deep Learning Frameworks
- 用Julia和Python构建三个开源库，集中管理RNN核心组件。
- 支持自定义扩展，方便测试不同RNN变体的性能差异。
- 适合需要快速实验RNN架构的研究者与工程师使用。
循环神经网络（RNN）是科学与工业领域序列建模的基础。过去十年中，为更好建模长程依赖并解决梯度消失与爆炸问题，提出了众多RNN变体。然而，缺乏统一的测试库，复现不同架构耗时且易出错，影响可复现性与探索效率。本文推出三个开源库：torchrecurrent、RecurrentLayers.jl 和 LuxRecurrentLayers.jl，分别基于Python和Julia实现，集中管理多种循环单元与高层架构。这些库提供一致的接口，支持灵活定制与实验，所有项目均采用MIT许可证，持续在GitHub维护。
原文摘要 · Abstract (English)
Recurrent neural networks (RNNs) are a cornerstone of sequence modeling across various scientific and industrial applications. Owing to their versatility, numerous RNN variants have been proposed over the past decade, aiming to improve the modeling of long-term dependencies and to address challenges such as vanishing and exploding gradients. However, no central library is available to test these variations, and reimplementing diverse architectures can be time-consuming and error-prone, limiting reproducibility and exploration. Here, we introduce three open-source libraries in Julia and Python that centralize numerous recurrent cell implementations and higher-level recurrent architectures. torchrecurrent, RecurrentLayers.jl, and LuxRecurrentLayers.jl offer a consistent framework for constructing and extending RNN models, providing built-in mechanisms for customization and experimentation. All packages are available under the MIT license and actively maintained on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。