|
Mashinani o’qitish tili fanidan
|
| bet | 11/11 | | Sana | 14.05.2024 | | Hajmi | 345,07 Kb. | | #232474 |
Bog'liq GRADIENT TUSHISH
XULOSA
Neyron tarmoqlarini turli sohalarda qo‘llanilishi tufayli ular asosida hal qilinadigan turli xil vazifalar shakllantirilmoqda, bu masalalar kirish ma’lumotlarining aniqlanishi va turlari bilan ajralib turadi, ya’ni tasvirlarni anglash, matnlarni tahlil qilish, kasalliklarni tashxislash va boshqa masalalarni hal qilishda neyron tarmoqlaridan foydalanilmoqda. Hisoblash tajribasi natijalari shuni ko‘rsatdiki, moment usuli va SGD turli xil konfiguratsiyalar tarmoqlari uchun berilgan ma’lumotlar to‘plamida eng yaxshi natijalarni ko‘rsatdi. SGD va moment usuli davomida erishilgan natijalarning aniqligi, xususan, dastlabki namuna muvozanatli ekanligi bilan izohlanadi, bu esa o‘z navbatida ushbu usullarning ishlashiga ijobiy ta’sir ko‘rsatadi.
FOYDALANILGAN ADABIYOTLAR
Jordan, J. Intro to optimization in deep learning: Gradient Descent/ J. Jordan // Paper-space. Series: Optimization. – 2018. – URL: https://blog.paperspace.com/intro-to- optimiza-tion-in-deep-learning-gradient-descent/
Scikit-learn – машинное обучение на Python. – URL: http://scikit- learn.org/stable/ modules/generated/sklearn.neural_network. MLPClassifier.html
Keras documentation: optimizers. – URL: https://keras.io/optimizers
Ruder, S. An overview of gradient descent optimization algorithms / S. Ruder // Cornell University Library. – 2016. – URL: https://arxiv. org/abs/1609.04747
Robbins, H. A stochastic approximation method / H. Robbins, S. Monro // The annals of mathematical statistics. – 1951. – Vol. 22. – P. 400–407.
Kukar, M. Cost-Sensitive Learning with Neural Networks / M. Kukar, I. Kononenko
// Machine Learning and Data Mining : proceed-ings of the 13th European Conference on Artifi-cial Intelligence. – 1998. – P. 445–449.
Duchi, J. Adaptive Subgradient Methods for Online Learning and Stochastic Optimiza-tion / J. Duchi, E. Hazan, Y. Singer // The Jour-nal of Machine Learning Research.
– 2011. – Vol. 12. – P. 2121–2159.
Zeiler, M. D. ADADELTA: An Adap-tive Learning Rate Method / Cornell Univer-sity Library. – 2012
|
| |
