Underfitting va Owerfitting

xmlns:w="urn:schemas-microsoft-com:office:word"
xmlns="http://www.w3.org/TR/REC-html40">
Maqitishda Underfitting va Owerfitting muammolari Regularization (moslashtirish,sozlash)

Mashish

Chiziqli regressiyada sozlash masalasi

Logistik regressiyada sozlash masalasi

Sozlash parametrini tanlash

Misol: Chiziqli regressiya (Uy narxi)
Overfitting: Agar bizda juda ko'p xususiyatlar mavjud bo'lsa, o'rganilgan Model training to'plamiga juda mos kelishi mumkin ( ), ammo yangi misollarni aniqlashda xatolik kata bosir qilish.

• Qoramiz).

Regularization(Mostlashtirish, sozlash).

• Barcha xususiyatlarni qoldirish, lekin parametrlarni kuchini op xususiyatlar bilan ishlash modelni qurishda goydali hisoblanadi. Ular ni aniqroq bashorat qilishda hissa qoOddiyroqyicha:
  
  
  
  • Xususiyatlar:
  • Parametrlar:
  
  Regularization (Mostlashtirish).
  Narxi
  

  Uy yuzasi

  
  Chiziqli regressiyada, minimum qilish uchun ni tanlash.
  

  Agar biz ni yetarlicha kata tanlasak nima sodir boladi?

  
  

  ( bu yerda deb nazarda tutulmoqda)

  
  

  Chiziqli regressiyada Regularization (Mostlashtirsh)

  
  Gradient descent
  Takrorlash
  
  
  

  Logistik regressiyada Regularization (Mostlashtirsh)

  
  Logistik regressiyada sozlash (Regularization ).
  Cost funksiyasi:
  

  x1
  x2

  
  Gradient descent
  

  Takrorlash

  
  

  Foydalanilgan adabiyotlar

  
  Aurelian Geron, Hands on Machine Learning with Scikit-Learn Keras&Tensorflow // Second edition Concepts, Tools, and Techniques to Build Intelligent Systems, 2019, 510 pages
  https://www.geeksforgeeks.org/ml-types-learning-supervised-learning/ https://www.guru99.com/unsupervised-machine-learning.html https://www.w3schools.com/python/python_ml_linear_regression.asp https://www.w3schools.com/python/python_ml_multiple_regression.asp https://www.w3schools.com/python/python_ml_polynomial_regression.asp https://www.mathworks.com/help/stats/regress.html
  http://fayllar.org