Computer and Communication Engineering, School of Computing and IT, Manipal University Jaipur, Jaipur, India.
Department of Electronics and Communication Engineering, Kalasalingam Academy of Research and Education, Virudhunagar, Tamilnadu, India.
Comput Intell Neurosci. 2022 Feb 21;2022:4725639. doi: 10.1155/2022/4725639. eCollection 2022.
Recently, long short-term memory (LSTM) networks are extensively utilized for text classification. Compared to feed-forward neural networks, it has feedback connections, and thus, it has the ability to learn long-term dependencies. However, the LSTM networks suffer from the parameter tuning problem. Generally, initial and control parameters of LSTM are selected on a trial and error basis. Therefore, in this paper, an evolving LSTM (ELSTM) network is proposed. A multiobjective genetic algorithm (MOGA) is used to optimize the architecture and weights of LSTM. The proposed model is tested on a well-known factory reports dataset. Extensive analyses are performed to evaluate the performance of the proposed ELSTM network. From the comparative analysis, it is found that the LSTM network outperforms the competitive models.
最近，长短期记忆 (LSTM) 网络被广泛应用于文本分类。与前馈神经网络相比，它具有反馈连接，因此它具有学习长期依赖关系的能力。然而，LSTM 网络存在参数调整问题。通常，LSTM 的初始和控制参数是基于试错法选择的。因此，在本文中，提出了一种进化 LSTM (ELSTM) 网络。使用多目标遗传算法 (MOGA) 来优化 LSTM 的架构和权重。所提出的模型在一个著名的工厂报告数据集上进行了测试。进行了广泛的分析来评估所提出的 ELSTM 网络的性能。从比较分析中发现，LSTM 网络优于竞争模型。
