XATOLIK FUNKSIYALARI: MCE, CROSS-ENTROPY VA BOSHQALAR
Keywords:
MSE, Cross-Entropy, xatolik funksiyasi, yo‘qotish funksiyasi, regressiya, tasniflash, gradient tushish, optimallashtirish.Abstract
Ushbu tezis sun’iy intellekt va mashinaviy o‘qitishda qo‘llaniladigan asosiy xatolik funksiyalarini, xususan MSE (Mean Squared Error), Cross-Entropy, MAE, Hinge Loss kabi funksiyalarni tahlil qiladi. Har bir xatolik funksiyasining matematik asoslari, qo‘llanish sohasi va afzallik-kamchiliklari yoritilgan. Modelning o‘qitilish jarayonida xatolik funksiyasining to‘g‘ri tanlanishi aniqlik, barqarorlik hamda konvergentsiya tezligiga ta’siri nuqtai nazaridan muhim ahamiyatga ega. Tadqiqotda tasniflash va regressiya masalalari uchun mos xatolik funksiyalarini solishtirish hamda optimal tanlov bo‘yicha tavsiyalar beriladi.
References
1. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
2. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
3. Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media.
4. Nielsen, M. A. (2015). Neural Networks and Deep Learning. Determination Press.
5. Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press.
6. Chollet, F. (2017). Deep Learning with Python. Manning Publications.
7. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. Springer.
8. Zhang, Z., & Sabuncu, M. R. (2018). Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels. Advances in Neural Information Processing Systems (NeurIPS).
9. Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (ICLR).
