Jump to content

AdaBoost: Revision history


For any version listed below, click on its date to view it. For more help, see Help:Page history and Help:Edit summary. (cur) = difference from current version, (prev) = difference from preceding version, m = minor edit, → = section edit, ← = automatic edit summary

(newest | oldest) View (newer 50 | ) (20 | 50 | 100 | 250 | 500)

23 November 2024

13 November 2024

28 October 2024

20 June 2024

  • curprev 07:5807:58, 20 June 2024 134.59.95.59 talk 25,690 bytes +45 Derivation: I learned a lot from the article and sincerely thank the authors. Just a small detail: In the derivation paragraph, after identifying the term in the error E that depends on k_{m}, we try to minimize it. Without constraint, this minimization with respect to k_{m} is performed for k_{m}(x_{i}) =y_{i}, i.e. the exact classifier. It's only because k_{m} is constrained to belong to an a priori set of classifiers that the solution is non-trivial. undo

29 April 2024

20 April 2024

6 March 2024

4 March 2024

1 September 2023

15 August 2023

16 June 2023

3 February 2023

29 January 2023

27 October 2022

13 September 2022

7 September 2022

1 August 2022

25 July 2022

24 June 2022

12 June 2022

5 June 2022

17 March 2022

11 February 2022

29 January 2022

22 November 2021

20 November 2021

18 September 2021

10 September 2021

31 July 2021

  • curprev 20:5020:50, 31 July 2021 Leopd talk contribs 24,534 bytes −1,040 Training: Removing overview paragraph which was confusingly irrelevant and incorrect. It contained true ML facts about the curse of dimensionality. But Adaboost has no concept of features, so this is irrelevant. Moreover the paragraph incorrectly stated that Adaboost considers which features to use, which it cannot as it is a meta learner. Only the learners can consider the raw features. undo Tags: Mobile edit Mobile web edit

26 May 2021

6 May 2021

4 May 2021

2 May 2021

22 April 2021

2 April 2021

14 March 2021

24 February 2021

25 January 2021

15 December 2020

13 December 2020

(newest | oldest) View (newer 50 | ) (20 | 50 | 100 | 250 | 500)