          機器學(xué)習(xí)基礎(chǔ) – 算法基礎(chǔ)培訓(xùn)

第九講: Linear Regression
weight vector for linear hypotheses and squared error instantly calculated by analytic solution

第十講: Logistic Regression
gradient descent on cross-entropy error to get good logistic hypothesis

第十一講: Linear Models for Classification
binary classification via (logistic) regression; multiclass classification via OVA/OVO decomposition

第十二講: Nonlinear Transformation
nonlinear model via nonlinear feature transform+linear model with price of model complexity

第十三講: Hazard of Overfitting
overfitting happens with excessive power, stochastic/deterministic noise and limited data

第十四講: Regularization
minimize augmented error, where the added regularizer effectively limits model complexity

第十五講: Validation
(crossly) reserve validation data to simulate testing procedure for model selection

第十六講: Three Learning Principles
be aware of model complexity, data goodness and your professionalism