1 / 34

Machine Learning Introduction

Machine Learning Introduction. Study on the Coursera All Right Reserved : Andrew Ng Lecturer: Much Database Lab of X iamen University. Aug 12,2014. Examples: Database mining Large datasets from growth of automation/web.

Download Presentation

Machine Learning Introduction

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. Machine Learning Introduction Study on the Coursera All Right Reserved : Andrew Ng Lecturer:Much Database Lab of Xiamen University Aug 12,2014

  2. Examples: • Database mining • Large datasets from growth of automation/web. • Web click data, medical records, biology, engineering • Applications can’t program by hand. • Handwriting recognition, most of Natural Language Processing (NLP), Computer Vision. • Machine Learning • Grew out of work in AI(Artificial Intelligence) • New capability for computers

  3. Machine Learning Definition • Tom Mitchell (1998) Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

  4. Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. What is the task T in this setting? T : Classifying emails as spam or not spam E : Watching you label emails as spam or not spam P: The number of emails correctly classified as spam/not spam “A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.”

  5. Machine Learning Algorithms • Supervised learning • Unsupervised learning • Others: • Reinforcement learning • Recommender systems.

  6. Supervised Learning & Unsupervised Learning x2 x1 Supervised Learning Unsupervised Learning

  7. Linear Regression with one Variable Housing Prices (Portland, OR) Price (in 1000s of dollars) Size (feet2) Supervised Learning Given the “right answer” for each example in the data. Regression Problem Predict real-valued output

  8. Training set of housing prices Notation: m = Number of training examples x’s = “input” variable / features y’s = “output” variable / “target” variable Training Set Learning Algorithm Estimated price h Size of house Question : How to describe h?

  9. Training Set Hypothesis: ‘s: Parameters How to choose ‘s ?

  10. Idea: Choose so that is close to for our training examples y x

  11. Cost Function Simplified: Hypothesis: Parameters: Cost Function: Goal:

  12. Price ($) in 1000’s Size in feet2 (x) Question:How to minimize J?

  13. Gradient Descent Have some function Want • Outline: • Start with some • Keep changing to reduce until we hopefully end up at a minimum

  14. Gradient descent algorithm Correct: Simultaneous update Incorrect:

  15. Gradient descent algorithm Notice : α is the learning rate.

  16. If α is too small, gradient descent can be slow. If α is too large, gradient descent can overshoot the minimum. It may fail to converge, or even diverge.

  17. at local optima Current value of Unchange Gradient descent can converge to a local minimum, even with the learning rate α fixed. As we approach a local minimum, gradient descent will automatically take smaller steps. So, no need to decrease α over time.

  18. Gradient Descent for Linear Regression Linear Regression Model Gradient descent algorithm

  19. Gradient descent algorithm update and simultaneously

  20. J(0,1) 1 0

  21. (for fixed , this is a function of x) (function of the parameters )

  22. (for fixed , this is a function of x) (function of the parameters )

  23. (for fixed , this is a function of x) (function of the parameters )

  24. (for fixed , this is a function of x) (function of the parameters )

  25. (for fixed , this is a function of x) (function of the parameters )

  26. (for fixed , this is a function of x) (function of the parameters )

  27. (for fixed , this is a function of x) (function of the parameters )

  28. (for fixed , this is a function of x) (function of the parameters )

  29. (for fixed , this is a function of x) (function of the parameters )

  30. Gradient descent: Linear Regression with multiple variables Repeat (simultaneously update for every ) Hypothesis: Parameters: Cost function:

  31. New algorithm : Gradient Descent Repeat Previously (n=1): Repeat (simultaneously update for ) (simultaneously update )

  32. Examples: simultaneously update

  33. Summarize • This is a briefly Introduction about Supervised Learning(Classification)in Machine Leaning. • There is still a lot of things in this subject,such as Clustering, Support Vector Machine(SVM), Dimensionality Reduction, ETC. The Core Idea of MS is very similar,hope you will be fond of the Machine Learning! Thanks for Listening !

More Related