Download presentation
Presentation is loading. Please wait.
Published byClementine Hensley Modified over 9 years ago
1
Probably Approximately Correct Learning Yongsub Lim Applied Algorithm Laboratory KAIST
2
Definition A class is PAC learnable by a hypothesis class if there is an algorithm such that over , # of i.i.d. training examples sampled from, such that where is an output of Probably Approximately Correct Learning2
3
Example Consider the class space which is the set of all positive half-lines An example is any real number Eg) Probably Approximately Correct Learning 1 0 3
4
Proof. is PAC learnable is PAC learnable by Probably Approximately Correct Learning4
5
Proof. is PAC learnable Our algorithm outputs a hypothesis such that Suppose for a positive example for a negative example Probably Approximately Correct Learning5
6
Proof. is PAC learnable Suppose, and it called only occurs if no training example Probably Approximately Correct Learning6
7
Proof. is PAC learnable Probably Approximately Correct Learning7
8
Proof. is PAC learnable Probably Approximately Correct Learning8
9
Proof. is PAC learnable The class is PAC learnable by itself with at least training examples Probably Approximately Correct Learning9
10
A More General Theorem Probably Approximately Correct Learning10
11
Thanks Probably Approximately Correct Learning 11
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.