跳转到内容

层 (深度学习)

维基百科,自由的百科全书

,或层次,是深度学习模型模型架构中的一种结构或网路拓扑,它从上一层获取信息,然后将信息传递给下一层。深度学习中有几个著名的层,即卷积神经网络中的卷积层[1]和最大池化层[2][3]。基本神经网络中的全连接层和ReLU层。循环神经网路中的RNN[4][5][6]自动编码器中的解卷积层等。

与新皮质层次的相异

[编辑]

深度学习新皮质的分层方式有本质上的分别:深度学习的分层取决于网路拓扑新皮质的分层取决于层内的同质性

参见

[编辑]

参考文献

[编辑]
  1. ^ Habibi, Aghdam, Hamed. Guide to convolutional neural networks : a practical application to traffic-sign detection and classification. Heravi, Elnaz Jahani. Cham, Switzerland. 2017-05-30. ISBN 9783319575490. OCLC 987790957. 
  2. ^ Yamaguchi, Kouichi; Sakamoto, Kenji; Akabane, Toshio; Fujimoto, Yoshiji. A Neural Network for Speaker-Independent Isolated Word Recognition. First International Conference on Spoken Language Processing (ICSLP 90). Kobe, Japan. November 1990 [2021-02-13]. (原始内容存档于2021-03-07). 
  3. ^ Ciresan, Dan; Meier, Ueli; Schmidhuber, Jürgen. Multi-column deep neural networks for image classification. New York, NY: Institute of Electrical and Electronics Engineers (IEEE). June 2012: 3642–3649. CiteSeerX 10.1.1.300.3283可免费查阅. ISBN 978-1-4673-1226-4. OCLC 812295155. S2CID 2161592. arXiv:1202.2745可免费查阅. doi:10.1109/CVPR.2012.6248110.  |journal=被忽略 (帮助)
  4. ^ Dupond, Samuel. A thorough review on the current advance of neural network structures.. Annual Reviews in Control. 2019, 14: 200–230 [2021-02-13]. (原始内容存档于2020-06-03). 
  5. ^ Abiodun, Oludare Isaac; Jantan, Aman; Omolara, Abiodun Esther; Dada, Kemi Victoria; Mohamed, Nachaat Abdelatif; Arshad, Humaira. State-of-the-art in artificial neural network applications: A survey. Heliyon. 2018-11-01, 4 (11): e00938. ISSN 2405-8440. PMC 6260436可免费查阅. PMID 30519653. doi:10.1016/j.heliyon.2018.e00938可免费查阅 (英语). 
  6. ^ Tealab, Ahmed. Time series forecasting using artificial neural networks methodologies: A systematic review. Future Computing and Informatics Journal. 2018-12-01, 3 (2): 334–340 [2021-02-13]. ISSN 2314-7288. doi:10.1016/j.fcij.2018.10.003可免费查阅. (原始内容存档于2021-11-29) (英语).