OʻRGATISH ALGORITMLARI: GRADIENT TUSHISHI, ADAM VA BOSHQALAR
Article Sidebar
Main Article Content
Abstract:
Maqolada mashinaviy oʻrganish tizimlarida model parametrlarini samarali oʻrgatish muammosi muammo–yechim yondashuvi asosida yoritiladi. Gradient tushishi, momentumga asoslangan yondashuvlar hamda Adam kabi adaptiv optimallashtirish algoritmlarining nazariy asoslari va ularning oʻrganish jarayonidagi roli izchil tahlil qilinadi. Turli algoritmlarning yaqinlashuv tezligi, barqarorligi va umumlashtirish qobiliyatiga taʼsiri ilmiy nuqtayi nazardan asoslanadi. Keltirilgan tahlillar optimallashtirish algoritmini ongli tanlash mashinaviy oʻrganish modellarining amaliy samaradorligini oshirishda muhim ahamiyatga ega ekanini koʻrsatadi.
Article Details
How to Cite:
References:
Bishop C. M. Pattern Recognition and Machine Learning. — New York: Springer, 2006. — 738 p.
Goodfellow I., Bengio Y., Courville A. Deep Learning. — Cambridge: MIT Press, 2016. — 775 p.
Haykin S. Neural Networks and Learning Machines. — 3rd ed. — New York: Pearson, 2009. — 936 p.
Bottou L. Stochastic Gradient Descent Tricks // Neural Networks: Tricks of the Trade. — Berlin: Springer, 2012. — P. 421–436.
Ruder S. An Overview of Gradient Descent Optimization Algorithms // arXiv preprint arXiv:1609.04747, 2016. — 14 p.
Kingma D. P., Ba J. Adam: A Method for Stochastic Optimization // International Conference on Learning Representations (ICLR). — San Diego, 2015. — 15 p.
Nocedal J., Wright S. Numerical Optimization. — 2nd ed. — New York: Springer, 2006. — 664 p.
LeCun Y., Bottou L., Orr G. B., Müller K. R. Efficient BackProp // Neural Networks: Tricks of the Trade. — Berlin: Springer, 2012. — P. 9–48.
Murphy K. P. Machine Learning: A Probabilistic Perspective. — Cambridge: MIT Press, 2012. — 1067 p.
Shalev-Shwartz S., Ben-David S. Understanding Machine Learning: From Theory to Algorithms. — Cambridge: Cambridge University Press, 2014. — 397 p.