GLOSSARY ENTRY (DERIVED FROM QUESTION BELOW) | ||||||
---|---|---|---|---|---|---|
|
07:32 Apr 11, 2020 |
English to Turkish translations [PRO] Science - Electronics / Elect Eng / digital imaging, artificial intelligent | |||||||
---|---|---|---|---|---|---|---|
|
| ||||||
| Selected response from: H&G Ozcan Türkiye Local time: 02:59 | ||||||
Grading comment
|
Summary of answers provided | ||||
---|---|---|---|---|
4 | başarım iyileştirme |
| ||
4 | seyreltme düzenleme yöntemi |
| ||
3 | terketme düzenlemesi |
|
terketme düzenlemesi Explanation: Dropout is a regularization technique patented by Google for reducing overfitting in neural networks by preventing complex co-adaptations on training data. The term "dropout" refers to dropping out units (both hidden and visible) in a neural network. Source: Wikipedia |
| |
Login to enter a peer comment (or grade) |
başarım iyileştirme Explanation: Metinde de geçtiği üzere derin öğrenmede kullanılan bir teknik. Overfitting sorunu için kullanılıyor genel olarak. Türkçe'de bu şekilde karşılanıyor genel olarak. https://www.coursera.org/lecture/deep-neural-network/dropout... |
| |
Login to enter a peer comment (or grade) |
seyreltme düzenleme yöntemi Explanation: Referans pdf dosyasında ayrıntılı olarak açıklanmış. https://dspace.ankara.edu.tr/xmlui/bitstream/handle/20.500.12575/68975/593535.pdf?sequence=1&isAllowed=y |
| |
Login to enter a peer comment (or grade) |
Login or register (free and only takes a few minutes) to participate in this question.
You will also have access to many other tools and opportunities designed for those who have language-related jobs (or are passionate about them). Participation is free and the site has a strict confidentiality policy.