Jaringan saraf konvolusional: Perbedaan antara revisi

'''Jaringan saraf konvolusional''' ([[bahasa Inggris]]: ''Convolutional neural network'' atau disingkat '''CNN''') adalah salah satu kelas [[Jaringan saraf umpan maju|jaringan saraf umpan-maju]] [[Regularisasi (matematika)|teregulasi]] yang secara mandiri mampu mempelajari [[rekayasa fitur]] melalui optimasi [[Filter (pemrosesan sinyal)|filter]] (atau kernel). Keunggulan CNN dibandingkan jaringan saraf sebelumnya terletak pada kemampuannya untuk mengatasi permasalahan gradien menghilang dan gradien meledak yang kerap muncul saat [[Algoritma perambatan mundur|propagasi balik]]. Hal ini dimungkinkan karena CNN menggunakan bobot terregularisasi pada koneksi yang lebih sedikit. <ref name="auto3">{{Cite book|last=Venkatesan|first=Ragav|last2=Li|first2=Baoxin|date=2017-10-23|url=https://books.google.com/books?id=bAM7DwAAQBAJ&q=vanishing+gradient|title=Convolutional Neural Networks in Visual Computing: A Concise Guide|publisher=CRC Press|isbn=978-1-351-65032-8|language=en|access-date=2020-12-13|archive-url=https://web.archive.org/web/20231016190415/https://books.google.com/books?id=bAM7DwAAQBAJ&q=vanishing+gradient#v=snippet&q=vanishing%20gradient&f=false|archive-date=2023-10-16|url-status=live}}</ref> <ref name="auto2">{{Cite book|last=Balas|first=Valentina E.|last2=Kumar|first2=Raghvendra|last3=Srivastava|first3=Rajshree|date=2019-11-19|url=https://books.google.com/books?id=XRS_DwAAQBAJ&q=exploding+gradient|title=Recent Trends and Advances in Artificial Intelligence and Internet of Things|publisher=Springer Nature|isbn=978-3-030-32644-9|language=en|access-date=2020-12-13|archive-url=https://web.archive.org/web/20231016190414/https://books.google.com/books?id=XRS_DwAAQBAJ&q=exploding+gradient#v=snippet&q=exploding%20gradient&f=false|archive-date=2023-10-16|url-status=live}}</ref> Misalnya, untuk ''setiap'' neuron di lapisan yang sepenuhnya terhubung (''fully connected layers''), diperlukan 10.000 bobot untuk memproses gambar berukuran 100 × 100 piksel. Namun, dengan menerapkan kernel ''konvolusi'' berjenjang (atau korelasi silang),<ref>{{Cite journal|last=Zhang|first=Yingjie|last2=Soon|first2=Hong Geok|last3=Ye|first3=Dongsen|last4=Fuh|first4=Jerry Ying Hsi|last5=Zhu|first5=Kunpeng|date=September 2020|title=Powder-Bed Fusion Process Monitoring by Machine Vision With Hybrid Convolutional Neural Networks|url=https://ieeexplore.ieee.org/document/8913613|journal=IEEE Transactions on Industrial Informatics|volume=16|issue=9|pages=5769–5779|doi=10.1109/TII.2019.2956078|issn=1941-0050|archive-url=https://web.archive.org/web/20230731120013/https://ieeexplore.ieee.org/document/8913613/|archive-date=2023-07-31|access-date=2023-08-12|url-status=live}}</ref><ref>{{Cite journal|last=Chervyakov|first=N.I.|last2=Lyakhov|first2=P.A.|last3=Deryabin|first3=M.A.|last4=Nagornov|first4=N.N.|last5=Valueva|first5=M.V.|last6=Valuev|first6=G.V.|date=September 2020|title=Residue Number System-Based Solution for Reducing the Hardware Cost of a Convolutional Neural Network|url=https://linkinghub.elsevier.com/retrieve/pii/S092523122030583X|journal=Neurocomputing|language=en|volume=407|pages=439–453|doi=10.1016/j.neucom.2020.04.018|archive-url=https://web.archive.org/web/20230629155646/https://linkinghub.elsevier.com/retrieve/pii/S092523122030583X|archive-date=2023-06-29|access-date=2023-08-12|quote=Convolutional neural networks represent deep learning architectures that are currently used in a wide range of applications, including computer vision, speech recognition, malware dedection, time series analysis in finance, and many others.|url-status=live}}</ref> hanya diperlukan 25 neuron untuk memproses petak berukuran 5x5.<ref name="auto1">{{Cite book|last=Habibi|first=Aghdam, Hamed|date=2017-05-30|title=Guide to convolutional neural networks : a practical application to traffic-sign detection and classification|location=Cham, Switzerland|isbn=9783319575490|others=Heravi, Elnaz Jahani|oclc=987790957}}</ref><ref>{{Cite journal|last=Atlas, Homma, and Marks|title=An Artificial Neural Network for Spatio-Temporal Bipolar Patterns: Application to Phoneme Classification|url=https://papers.nips.cc/paper/1987/file/98f13708210194c475687be6106a3b84-Paper.pdf|journal=Neural Information Processing Systems (NIPS 1987)|volume=1|archive-url=https://web.archive.org/web/20210414091306/https://papers.nips.cc/paper/1987/file/98f13708210194c475687be6106a3b84-Paper.pdf|archive-date=2021-04-14|url-status=live}}</ref> Arsitektur CNN ini memungkinkan ekstraksi fitur tingkat tinggi dari jendela konteks yang lebih luas pada lapisan yang lebih tinggi dibanding lapisan sebelumnya.

 

 

* [[Visi komputer|pengenalan citra dan video]], <ref name="Valueva Nagornov Lyakhov Valuev 2020 pp. 232–243">{{Cite journal|last=Valueva|first=M.V.|last2=Nagornov|first2=N.N.|last3=Lyakhov|first3=P.A.|last4=Valuev|first4=G.V.|last5=Chervyakov|first5=N.I.|year=2020|title=Application of the residue number system to reduce hardware costs of the convolutional neural network implementation|journal=Mathematics and Computers in Simulation|publisher=Elsevier BV|volume=177|pages=232–243|doi=10.1016/j.matcom.2020.04.031|issn=0378-4754|quote=Convolutional neural networks are a promising tool for solving the problem of pattern recognition.}}</ref>