| 本文已被：浏览 791次 下载 1685次 |
码上扫一扫！ |
|
|
| 增量构造式随机循环神经网络 |
|
李文艺1,2,3, 代伟1,2, 南静1,2, 刘从虎3
|
|
1.中国矿业大学 人工智能研究院, 江苏 徐州 221116;2.中国矿业大学 信息与控制工程学院, 江苏 徐州 221116;3.宿州学院 机械与电子工程学院, 安徽 宿州 234000
|
|
| 摘要: |
| 针对循环神经网络(recurrent neural network, RNN)的结构不易确定、参数学习过程复杂等问题, 提出一种增量构造式随机循环神经网络(incremental-construction for random RNN, IRRNN), 实现了RNN结构的增量构造与参数的随机学习. 首先建立隐含节点增量构造的约束机制, 同时利用候选节点池策略实现隐含节点的优选, 避免了网络随机构造的盲目性; 进一步, 从模型参数的局部优化与全局优化两个角度考虑, 提出模型参数的两种增量随机(incremental random, IR)学习方法, 即IR-1与IR-2, 并证明了其万能逼近特性; 同时通过研究IRRNN的动态特性, 分析了IRRNN的泛化性能. 通过实验验证了IRRNN在动态特性、紧凑性和精度等多个方面具有良好特性. |
| 关键词: 增量构造 随机学习 随机权神经网络 循环神经网络 稳定性 |
| DOI：10.13328/j.cnki.jos.007257 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金(61973306, 62373361); 江苏省优秀青年基金(BK20200086); 安徽省教育厅重点项目(2022AH051361, 2023AH052233) |
|
| Incremental-construction for Random Recurrent Neural Network |
|
LI Wen-Yi1,2,3, DAI Wei1,2, NAN Jing1,2, LIU Cong-Hu3
|
|
1.Artificial Intelligence Research Institute, China University of Mining and Technology, Xuzhou 221116, China;2.School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China;3.School of Mechanical and Electronic Engineering, Suzhou University, Suzhou 234000, China
|
| Abstract: |
| Due to the difficulty in determining the structure and training the parameters of recurrent neural network (RNN), an incremental-construction for random RNN (IRRNN) is proposed to realize the incremental construction of RNN structures and the random learning of network parameters. The IRRNN establishes an incremental constraint mechanism for hidden nodes and uses the candidate node pool strategy to realize the optimal selection of hidden nodes, avoiding the blindness of random construction of the network. Two incremental random learning methods, termed IR-1 and IR-2, are designed for local and global optimization of model parameters. Additionally, their universal approximation property is proved. Meanwhile, the dynamic property of the IRRNN model is studied to analyze its generalization performance. Experiments validated that the IRRNN exhibits favorable dynamic properties, compactness, and accuracy. |
| Key words: incremental construction random learning random weight neural network recurrent neural network (RNN) stability |
