1 / 20

the feasibility of machine learning

the feasibility of machine learning . Component of learning. Formalization Input (输入) :X (customer application) think of it as deed dimension vector Output (输出) :Y(+1,-1) good/bad customer Target Function( 目标函数 ) : f :x → y ideal credit approval formula. Component of learning.

ula
Download Presentation

the feasibility of machine learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. the feasibility of machine learning

  2. Component of learning • Formalization • Input(输入):X (customer application) think of it as deed dimension vector • Output(输出):Y(+1,-1) good/bad customer • Target Function(目标函数) : f :x→y ideal credit approval formula Company Logo

  3. Component of learning • Formalization • Data(数据): (), (),…, () historical records ↓↓↓ • Hypothesis(假设) :g :x→y 为了得到目标函数的公式 F is unknown G is very much known actually we created it Company Logo

  4. Component of learning UNKNOWN TARGET FUNCTION f :x→y ↓ ↓ TRAINING EXAMPLES (), (),…, () FINAL HYPOTHESIS g (G hopefully approximates F) Company Logo

  5. Component of learning UNKNOWN TARGET FUNCTION f :x→y ↓ ↓ TRAINING EXAMPLES (), (),…, () FINAL HYPOTHESIS g (G hopefully approximates F) Company Logo

  6. Component of learning TRAINING EXAMPLES (), (),…, () LEARNING ALGORITHM →HYPOTHESIS SET (从现实模型公式中创造公式) (将它们成为假设集) FINAL HYPOTHESIS Company Logo

  7. Component of learning HYPOTHESIS SET H 从假设集选出一个假设 H 衍生出一堆H’s(待定函数) Company Logo

  8. Component of learning UNKNOWN TARGET FUNCTION f :x→y ↓ ↓ TRAINING EXAMPLES (), (),…, () FINAL HYPOTHESIS g (G hopefully approximates F) Company Logo

  9. HYPOTHESIS SET • Hypothesis Set • H = {h} g∈ H • Learning Algorithm • Together. they are referred to as the learning model. a hypothesis set and a learning algorithm Company Logo

  10. A simplehypothesis set—’perceptron’ • For input X= attributes of a customer • Approve credit if > threshold • Deny credit if < threshold This linear formula h∈ H can be written as h(x) = sign( ()– threshold ) Company Logo

  11. Learning Feasible Company Logo

  12. Learning Feasible • A related experiment P(picking red)=μ P(picking green)=1-μ μ=probability of red marbles Company Logo

  13. Learning Feasible Pick N marbles independently The fraction of red marbles in sample =v Company Logo

  14. Does v Say anything about μ? • NO! Sample can be mostly green while bin is mostly red Company Logo

  15. Does v Say anything about μ? • Yes Sample frequency v is close to bin frequency μ This is called Hoeffding Inequality Company Logo

  16. Learning Feasible • Bin • Unknown is a number μ • Learning • Unknown is a function f:x→y each marble is a point x ∈ X Company Logo

  17. Learning Feasible • Bin • Unknown is a number μ • Learning • Unknown is a function f:x→y each marble is a point x ∈ X Hypothesis got it right h(x)=f(x) Company Logo

  18. Learning Feasible • Bin • Unknown is a number μ • Learning • Unknown is a function f:x→y each marble is a point x ∈ X Hypothesis got it wrong h(x)≠f(x) Company Logo

  19. Learning Feasible UNKNOWN TARGET FUNCTION f :x→y ↓ ↓ TRAINING EXAMPLES (), (),…, () FINAL HYPOTHESIS g (G hopefully approximates F) Company Logo

  20. Learning Feasible Probability distribution P on X Company Logo

More Related