基于残差的门控循环单元

张忠豪; 董方敏; 胡枫; 吴义熔; 孙水发

doi:10.16383/j.aas.c190591

基于残差的门控循环单元

doi: 10.16383/j.aas.c190591

张忠豪^1,,
董方敏^1,,
胡枫^1,,
吴义熔^{1, 2,},
孙水发^{1, 2,}

1.
三峡大学计算机与信息学院宜昌 443002
2.
智慧医疗宜昌市重点实验室宜昌 443002

基金项目: 国家自然科学基金(U1703261, 61871258), 国家重点研发计划(2016-YFB0800403)资助

详细信息

作者简介:
张忠豪：三峡大学硕士研究生. 主要研究方向为人工智能和自然语言处理. E-mail: zhangminecraftbiu@gmail.com

董方敏：三峡大学教授. 主要研究方向为计算图形学, 计算机视觉和人工智能. E-mail: fmdong@ctgu.edu.cn

胡枫：三峡大学硕士研究生. 主要研究方向为自然语言处理. E-mail: h18271692608@163.com

吴义熔：三峡大学教授. 主要研究方向为人工智能和自然语言处理. E-mail: yirongwu@gmail.com

孙水发：三峡大学教授. 主要研究方向为多媒体信息处理和智能信息处理. 本文通信作者.E-mail: watersun@ctgu.edu.cn

计量
- 文章访问数: 623
- HTML全文浏览量: 271
- PDF下载量: 169
- 被引次数: 0
出版历程
- 收稿日期: 2019-08-18
- 录用日期: 2020-01-17
- 网络出版日期: 2022-12-23
- 刊出日期: 2022-12-23

Residual Based Gated Recurrent Unit

ZHANG Zhong-Hao^1
,,
DONG Fang-Min^1
,,
HU Feng^1
,,
WU Yi-Rong^{1, 2
,},
SUN Shui-Fa^{1, 2
,}

1.
College of Computer and Information Technology, China Three Gorges University, Yichang 443002
2.
Yichang Key Laboratory of Intelligent Medicine, Yichang 443002

Funds: Supported by National Natural Science Foundation of China (U17-03261, 61871258) and National Key Research and Development Pro-ject (2016YFB0800403)

More Information

Author Bio:
ZHANG Zhong-Hao　Master student at China Three Gorges University. His research interest covers artifici-al intelligence and nature language processing

DONG Fang-Min　Professor at China Three Gorges University. His research interest covers computer graphics, computer vision and artificial intelligence

HU Feng　Master student at China Three Gorges University. His main research interest is nature language pro-cessing

WU Yi-Rong　Professor at China Three Gorges University. His research interest covers artificial intelligence and nature language processing

SUN Shui-Fa　Professor at China Three Gorges University. His research interest covers multi-media information processing and intelligent information processing. Corresponding author of this paper

摘要

摘要: 传统循环神经网络易发生梯度消失和网络退化问题. 利用非饱和激活函数可以有效克服梯度消失的性质, 同时借鉴卷积神经网络中的残差结构能够有效缓解网络退化的特性, 在门控循环神经网络(Gated recurrent unit, GRU)的基础上提出了基于残差的门控循环单元(Residual-GRU, Re-GRU)来缓解梯度消失和网络退化问题. Re-GRU的改进主要包括两个方面: 1)将原有GRU的候选隐状态的激活函数改为非饱和激活函数; 2)在GRU的候选隐状态表示中引入残差信息. 对候选隐状态激活函数的改动不仅可以有效避免由饱和激活函数带来的梯度消失问题, 同时也能够更好地引入残差信息, 使网络对梯度变化更敏感,从而达到缓解网络退化的目的. 进行了图像识别、构建语言模型和语音识别3类不同的测试实验, 实验结果均表明, Re-GRU拥有比对比方法更高的检测性能, 同时在运行速度方面优于Highway-GRU和长短期记忆单元. 其中, 在语言模型预测任务中的Penn Treebank数据集上取得了23.88的困惑度, 相比有记录的最低困惑度, 该方法的困惑度降低了一半.
- 深度学习 /
- 循环神经网络 /
- 门控循环单元 /
- 残差连接
Abstract: Traditional recurrent neural networks are prone to the problems of vanishing gradient and degradation. Relying on the facts that non-saturated activation functions can effectively overcome the vanishing gradient problem, and the residual structure in convolution neural network can effectively alleviate the degradation problem, we propose a residual−gated recurrent unit (Re-GRU) which leverages gated recurrent unit (GRU) to alleviate the problems of vanishing gradient and degradation. There are two main improvements in Re-GRU. One is to replace the activation function of the candidate hidden state in GRU with the non-saturated activation function. The other is to introduce the residual information into the candidate hidden state representation of the GRU. The modification of candidate hidden state activation function can not only effectively avoid vanishing gradient caused by non-saturated activation function, but also introduce residual information to make the network more sensitive to gradient change, so as to alleviate the degradation problem. We conducted three kinds of test experiments, including image recognition, building language model, and speech recognition. The results indicate that our proposed Re-GRU has higher detection performance than other 6 methods. Specifically, we achieved a test-set perplexity of 23.88 on the Penn Treebank data set in language model prediction task, which is one half of the lowest value ever recorded.
- Deep learning /
- recurrent neural networks /
- gated recurrent unit /
- skip connect

HTML全文

图 1 GRU单元结构

Fig. 1 GRU structure

下载: 全尺寸图片幻灯片

图 2 高速公路网络结构

Fig. 2 Highway-network structure

下载: 全尺寸图片幻灯片

图 3 残差网络结构^[11]

Fig. 3 Residual-Networks structure^[11]

下载: 全尺寸图片幻灯片

图 4 Re-GRU结构

Fig. 4 Re-GRU structure

下载: 全尺寸图片幻灯片

图 5 7层网络的GRU、GRU-relu、Re-GRU在MNIST数据集上的损失变化曲线

Fig. 5 Loss curve of GRU, GRU-relu and Re-GRU on the MNIST data set of a seven-layer network

下载: 全尺寸图片幻灯片

图 6 GRU与Re-GRU在PTB数据集上的损失值变化曲线

Fig. 6 Loss curve of GRU and Re-GRU on PTB dataset

下载: 全尺寸图片幻灯片

图 7 GRU与Re-GRU在TIMIT数据集上的损失值变化曲线

Fig. 7 Loss curve of GRU and Re-GRU on TIMIT dataset

下载: 全尺寸图片幻灯片

表 1 MNIST数据集测试结果 (%)

Table 1 MNIST dataset test results (%)

模型	1 层网络	3 层网络	5 层网络	7 层网络	9 层网络
RNN	52	12	9	10	10
GRU	92	92	11	11	10
LSTM	94	91	10	9	10
RNN-relu	67	72	63	56	9
GRU-relu	93	93	80	76	11
SRU	86	94	93	93	93
Highway-GRU	89	95	94	92	33
Re-GRU	97	96	94	95	94

下载: 导出CSV

表 2 PTB的测试结果 (PPL, s)

Table 2 PTB dataset test results (PPL, s)

模型	3 层网络	5 层网络	7 层网络
RNN	142.37, 149	135.56, 188	143.68, 214
GRU	59.73, 467	50.03, 584	50.25, 750
LSTM	56.42, 409	41.03, 542	84.27, 915
RNN-relu	125.83, 81	115.79, 164	117.32, 257
GRU-relu	96.71, 453	57.03, 602	90.14, 763
SRU	104.93, 206	124.18, 334	143.77, 432
Highway-GRU	99.77, 523	108.13, 834	88, 1176
Re-GRU	24.32, 378	23.88, 682	25.14, 866

下载: 导出CSV

表 3 WikiText-2的测试结果(PPL, s)

Table 3 WikiText-2 dataset test results (PPL, s)

模型	7 层网络
RNN	155.43, 235
GRU	43.87, 618
LSTM	29.00, 733
SRU	159.39, 514
Re-GRU	23.88, 644

下载: 导出CSV

表 4 TIMIT的测试结果(%, s)

Table 4 TIMIT dataset test results (%, s)

模型	3 层网络	5 层网络	7 层网络
RNN	22.5, 151	23.7, 225	23.9, 295
GRU	18.3, 389	18.2, 620	18.5, 854
LSTM	17.4, 478	17.2, 777	17.9, 1080
RNN-relu	18.3, 154	18.4, 239	18.6, 302
GRU-relu	17.3, 385	17.9, 616	17.8, 853
SRU	17.4, 404	18.3, 656	18.4, 924
Highway-GRU	18.0, 549	18.1, 908	17.5, 1294
Li-GRU	17.6, 287	17.9, 478	18.1, 630
Re-GRU	17.8, 427	17.5, 703	17.1, 984

下载: 导出CSV

参考文献(25)

[1]	Graves A, Jaitly N, Mohamed A. Hybrid speech recognition with deep bidirectional LSTM. In: Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding. Olomouc, Czech Republic: 2013. 273−278
[2]	Mikolov T, Zweig G. Context dependent recurrent neural network language model. In: Proceedings of the 2012 IEEE Spoken Language Technology Workshop. Miami, USA: 2012. 234−239
[3]	Zhao B, Tam Y C. Bilingual recurrent neural networks for improved statistical machine translation. In: Proceedings of the 2014 IEEE Spoken Language Technology Workshop. South Lake Tahoe, USA: 2014. 66−70
[4]	奚雪峰, 周国栋. 面向自然语言处理的深度学习研究. 自动化学报, 2016, 42(10): 1445-1465 Xi Xue-Feng, Zhou Guo-Dong. A survey on deep learning for natural language processing. Acta Automatica Sinica, 2016, 42(10): 1445-1465
[5]	Hochreiter S. The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 1998, 6(02): 107-116 doi: 10.1142/S0218488598000094
[6]	Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation, 1997, 9(8): 1735-1780 doi: 10.1162/neco.1997.9.8.1735
[7]	Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. Kuching, Malaysia, 2014: 3104−3112
[8]	Morgan N. Deep and wide: Multiple layers in automatic speech recognition. IEEE. Transactions on Audio, Speech, and Language Processing, 2011, 20(1): 7−13
[9]	Srivastava R K, Greff K, Schmidhuber J. Training very deep networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada: 2015. 2377−2385
[10]	Orhan E, Pitkow X. Skip Connections eliminate singularities. In: Proceedings of the International Conference on Learning Representations. Vancouver, Canada: 2018. 1−22
[11]	He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: 2016. 770−778
[12]	Lei T, Zhang Y, Wang S I, Dai H, Artzi Y. Simple recurrent units for highly parallelizable recurrence. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium: 2018. 4470−4481
[13]	张文, 冯洋, 刘群. 基于简单循环单元的深层神经网络机器翻译模型. 中文信息学报, 2018, 32(10): 36-44 doi: 10.3969/j.issn.1003-0077.2018.10.006 Zhang Wen, Feng Yang, Liu Qun. Deep Neural Machine Translation Model Based on Simple Recurrent Units. Journal of Chinese Information Processing, 2018, 32(10): 36-44 doi: 10.3969/j.issn.1003-0077.2018.10.006
[14]	Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning. Lille, France: 2015. 448−456
[15]	Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. Sardinia, Italy: 2010: 249−256
[16]	Ravanelli M, Brakel P, Omologo M, et al. Light gated recurrent units for speech recognition. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018, 2(2): 92-102 doi: 10.1109/TETCI.2017.2762739
[17]	Vydana H K, Vuppala A K. Investigative study of various activation functions for speech recognition. In: Proceedings of the 23th National Conference on Communications. Chennai, India: 2017. 1−5
[18]	Deng L. The MNIST database of handwritten digit images for machine learning research[best of the web]. IEEE Signal Processing Magazine, 2012, 29(6): 141-142 doi: 10.1109/MSP.2012.2211477
[19]	Marcus M P, Marcinkiewicz M A, Santorini B. Building a Large Annotated Corpus of English: The Penn Treebank. Computational Linguistics, 2002, 19(2): 313-330
[20]	Melis G, Dyer C, Blunsom P. On the state of the art of evaluation in neural language models. In: Proceedings of the 2018 International Conference on Learning Representations. Vancouver, Canada: 2018. 1−10
[21]	Ravanelli M, Parcollet T, Bengio Y. The Pytorch-Kaldi speech recognition toolkit. In: Proceedings of the ICASSP 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. Brighton, UK: 2019. 6465−6469
[22]	Oualil Y, Klakow D. A Neural Network approach for mixing language models. In: Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing. New Orleans, USA: IEEE, 2017. 5710−5714
[23]	Zue V, Seneff S, Glass J. Speech database development at MIT: TIMIT and beyond. Speech communication, 1990, 9(4): 351-356 doi: 10.1016/0167-6393(90)90010-7
[24]	Arnab G, Gilles B, Luk＇as B, Ondrej G, Nagendra G, Mirko H, et al. The Kaldi speech recognition toolkit. In: Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding. Hawaii, USA: 2011. 59−64
[25]	Le Q V, Jaitly N, Hinton G E. A simple way to initialize recurrent networks of rectified linear units. arXiv preprint, 2015, arXiv: 1504.00941