Classification and Regression Models in Machine Learning
Explore the concepts of classification and regression in machine learning through content covering topics like softmax, loss functions, and optimization difficulties. Learn about one-hot vectors, output values, and the importance of choosing the right loss function for effective model training.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Classification (Short Version) Hung-yi Lee 1
Classification To learn more https://youtu.be/fZAZUYEeIMg (in Mandarin) https://youtu.be/hSXFuypLukA (in Mandarin) 2
Classification as Regression? Regression ? ? Model ? Classification as regression? ? ? Model ? class 1 = class 1 2 = class 2 3 = class 3 similar? different? 3
Class 2 Class 3 Class 1 Class as one-hot vector 0 1 0 0 0 1 1 0 0 or or ? = ?1 ?1 + ?1 only output one value 1 ?2 ? ?2 + ?2 + ? ?3 1 1 How to output multiple values? ?3 ?3 + 1 4
Class 2 Class 3 Class 1 Class as one-hot vector 0 1 0 0 0 1 1 0 0 or or ? = ?1 ?1 ?1 + + ?1 1 1 ?2 ?2 ?2 ?2 + + ?3 1 1 ?3 ?3 ?3 + + 1 1 5
Regression feature label ? ?? = ? ? ? ? ? + ? + Classification feature ? = ? ? + ? ? ? ? + ? ? = ??????? ? label Make all values between 0 and 1 0 or 1 Can have any value 6
??? ?? ???? ?? > 0 = 1 1 > ?? ??? Soft-max = ?? How about binary classification? Softmax 0.88 ?1 3 20 20 e ?1 0.12 ?2 1 2.7 2.7 e ?2 0 ?3 -3 0.05 0.05 e ?3 logit + 7
Loss of Classification ? =1 ? ?? ? label softmax ? ? ? ? Network ? 2 ?? ?? ? = Mean Square Error (MSE) ? Cross-entropy ?????? ? = ? Minimizing cross-entropy is equivalent to maximizing likelihood. 8
http://speech.ee.ntu.edu.tw/~tlkagk/courses/MLDS_2015_2/Lecture/Deep%20More%20(vhttp://speech.ee.ntu.edu.tw/~tlkagk/courses/MLDS_2015_2/Lecture/Deep%20More%20(v 2).ecm.mp4/index.html ?1 ?2 ?3 -10 ~ 10 ?1 ?2 ?3 1 0 0 softmax -10 ~ 10 ? Network ? -1000 large loss Cross-entropy Mean Square Error (MSE) large loss stuck! ?2 ?2 small loss small loss ?1 ?1 Changing the loss function can change the difficulty of optimization. 9
