Lecture "Applied data science: Learning process and Bias – variance tradeoff" includes content: learning process, bias – variance tradeoff, variance tradeoff, bias variance, . We invite you to consult! | Applied Data Science Sonpvh 2022 1 1. Introduction 8. Validation 2. Application 9. Regularization 3. EDA 10. Clustering 4. Learning Process 11. Evaluation 5. Bias Variance TradeOff 12. Deployment 6. Regression 13. Ethics 7. Classification 2 UNKNOWN TARGET FUNCTION Υ Training sample x y x y g x x Learning Final Hypothesis algorithms g Υ Hypothesis Set ℋ Learning From Data Yaser 1 3 Probability Distribution P on AWARENESS GOOD vs BAD Age INTEREST Υ Salary Job status Household size LEAD FORM . x x xN Training sample TELESALE x y x y g x x Learning ELIGIBILITY Final Hypothesis algorithms g Υ GOOD vs BAD y 1 0 DISBURSED Hypothesis Set What is eligibility label definition ℋ 4 Learning purpose g x x Binary error e g ۤ x g x ۥ But What does g x x mean ERROR MEASURE e g Squared error e g x g x 2 Supermarket verify for CIA verify for security 5 Learning From Data Yaser 1 discount UNKNOWN TARGET DISTRIBUTION UNKNOWN TARGET FUNCTION Probability Distribution g given x Training set Target function Υ NOISE P on g given x Test set xtrain ERROR xtest Training sample g x x in 0 MEASURE e x y x y g x x Learning feasible Learning Final Hypothesis algorithms g Υ Hypothesis Set ℋ Learning From Data Yaser 1 6 Purposes Measure Metrics Target population Target Non Target definition What are the use cases Exclusions . What Where When How to collect data UNKNOWN TARGET DISTRIBUTION Probability Business Data Target function Υ Distribution P on Understand Understand Noise ing ing xtrain xtest ERROR Data Training MEASURE e sample Preparation x y x y g x x Final Deploymen Learning Hypothesis Modeling algorithms g Υ t Evaluation Hypothesis Set ℋ Learning process Data Unify Data Governance 7 Learning purpose With probability 1- in 0 Approximati Eout g Ein g Ω N on Generalizati model complexity N sample size. confidence on requirement Approximation Generalization trade-off More complex H better chance of approximation f Less complex H better chance of generalizing out of sample 8 Learning From .