層 (深度學習)

層，或層次，是深度學習模型模型架構中的一種結構或網路拓撲，它從上一層獲取信息，然後將信息傳遞給下一層。深度學習中有幾個著名的層，即卷積神經網絡中的卷積層^[1]和最大池化層^[2]^[3]。基本神經網絡中的全連接層和ReLU層。循環神經網路中的RNN層^[4]^[5]^[6]和自動編碼器中的解卷積層等。

與新皮質層次的相異

深度學習與新皮質的分層方式有本質上的分別：深度學習的分層取決於網路拓撲，新皮質的分層取決於層內的同質性。

參見

參考文獻

^ 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.
^ 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]. （原始內容存檔於2021-03-07）.
^ 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  . ISBN 978-1-4673-1226-4. OCLC 812295155. S2CID 2161592. arXiv:1202.2745  . doi:10.1109/CVPR.2012.6248110. |journal=被忽略 (幫助)
^ Dupond, Samuel. A thorough review on the current advance of neural network structures.. Annual Reviews in Control. 2019, 14: 200–230 [2021-02-13]. （原始內容存檔於2020-06-03）.
^ 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  . PMID 30519653. doi:10.1016/j.heliyon.2018.e00938  （英語）.
^ 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  . （原始內容存檔於2021-11-29）（英語）.

[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.

[Yamaguchi111990-2] 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]. （原始內容存檔於2021-03-07）.

[mcdns-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  . ISBN 978-1-4673-1226-4. OCLC 812295155. S2CID 2161592. arXiv:1202.2745  . doi:10.1109/CVPR.2012.6248110. |journal=被忽略 (幫助)

[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]. （原始內容存檔於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  . PMID 30519653. doi:10.1016/j.heliyon.2018.e00938  （英語）.

[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  . （原始內容存檔於2021-11-29）（英語）.

[1]

[2]

[3]

[4]

[5]

[6]