期刊文献+

基于自适应学习率的深度信念网设计与应用 被引量:20

Design and Application of Deep Belief Network with Adaptive Learning Rate
下载PDF
导出
摘要 针对深度信念网(Deep belief network,DBN)预训练耗时长的问题,提出了一种基于自适应学习率的DBN(Adaptive learning rate DBN,ALRDBN).ALRDBN将自适应学习率引入到对比差度(Contrastive divergence,CD)算法中,通过自动调整学习步长来提高CD算法的收敛速度.然后设计基于自适应学习率的权值训练方法,通过网络性能分析给出学习率变化系数的范围.最后,通过一系列的实验对所设计的ALRDBN进行测试,仿真实验结果表明,ALRDBN的收敛速度得到了提高且预测精度也有所改善. A deep belief network with adaptive learning rate (ALRDBN) is proposed to solve the time-consuming problem in the pre-training period of DBN. The ALRDBN introduces the idea of adaptive learning rate into contrastive divergence (CD) algorithm and accelerates its convergence by a self-adjusting learning rate. The training method of weights in this case is designed, in which the adjusting scope of the coefficient in learning rate is determined by performance analysis. Finally, a series of experiments are carried out to test the performance of ALRDBN, and the corresponding results show that the convergence rate is accelerated significantly and the accuracy of prediction is improved as well.
出处 《自动化学报》 EI CSCD 北大核心 2017年第8期1339-1349,共11页 Acta Automatica Sinica
基金 国家自然科学基金(61533002 61473034) 国家杰出青年科学基金(61225016) 内涵发展-引进人才科研启动费资助~~
关键词 深度信念网 自适应学习率 对比差度 收敛速度 性能分析 Deep belief network, adaptive learning rate, contrastive divergence, convergence rate, performance analysis
  • 相关文献

参考文献5

二级参考文献161

  • 1梁美彦,赵树森,沈京玲,等.利用径向基神经网络对毒品太赫兹光谱的识别[J].光学学报,2009,29:226-230.
  • 2Hinton G E, Salakhutdinov R R. Reducing the dimensional- ity of data with neural networks. Science, 2006, 313(5786): 504-507.
  • 3Hinton G E, Osindero S, Teh Y W. A fast learning algo- rithm for deep belief nets. Neural Computation, 2006 18(7): 1527-1554.
  • 4Deselaers T, Hasan S, Bender O, Ney H. A deep learning approach to machine transliteration. In: Proceedings of the 4th EACL Workshop on Statistical Machine Translation. Athens, Greece: Association for Computational Linguistics, 2009. 233--241.
  • 5Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533-536.
  • 6Bengio Y, Lamblin P, Popovici D, Larochelle H. Greedy layer-wise training of deep networks. In: Proceedings of the 20th Advances in Neural Information Processing Sys- tems. Vancouver, British Columbia, Canada: NIPS, 2007. 153-160.
  • 7Arel I, Rose D C, Karnowski T P. Deep machine learning- a new frontier in Artificial intelligence research. IEEE Com- putational Intelligence Magazine, 2010, 5(4): 13-18.
  • 8Dahl G E, Dong Y, Deng L, Acero A. Large vocabulary con- tinuous speech recognition with context-dependent DBN- HMMS. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing. Prague: IEEE, 2011. 4688-4691.
  • 9Fasel I, Berry J. Deep belief networks for real-time extrac- tion of tongue contours from ultrasound during speech. In: Proceedings of the 20th International Conference on Pattern Recognition. Istanbuh IEEE, 2010. 1493--1496.
  • 10Zhang S L, Bao Y B, Zhou P, Jiang H, Dai L R. Improving deep neural networks for LVCSR using dropout and shrink- ing structure. In: Proceedings of the 2014 IEEE Interna- tional Conference on Acoustics, Speech and Signal Process- ing (ICASSP). Florence: IEEE, 2014. 6849-6853.

共引文献81

同被引文献160

引证文献20

二级引证文献134

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部