Presentation is loading. Please wait.

Presentation is loading. Please wait.

IES 511 Machine Learning Dr. Türker İnce (Lecture notes by Prof. T. M

Similar presentations


Presentation on theme: "IES 511 Machine Learning Dr. Türker İnce (Lecture notes by Prof. T. M"— Presentation transcript:

1 IES 511 Machine Learning Dr. Türker İnce (Lecture notes by Prof. T. M
IES 511 Machine Learning Dr. Türker İnce (Lecture notes by Prof. T. M. Mitchell, Machine Learning course at CMU) Concept Learning General-to-Specific Ordering of Hypothesis Find-S and Candidate Elimination Algorithms Inductive Bias

2 Learning System Design Example - Play Checkers

3 Concept Learning Example

4 Hypothesis representation

5 Concept Learning Task

6 Fundamental assumption of inductive learning

7 General-to-specific ordering of hypothesis

8 The Find-S Algorithm

9 Hypothesis space search by Find-S

10 Limitations of Find-S Can’t tell whether it has learned concept
Can’t tell when training data inconsistent Picks a maximally specific h (why?) Depending on H, there might be several!

11 Consistent hypothesis and Version Space

12 The List-Then-Eliminate Algorithm

13 Version Space of EnjoySport Concept Learning

14 Version Space of EnjoySport Concept Learning

15 Candidate Elimination Algorithm

16 Candidate Elimination Algorithm

17 EnjoySport Example

18 EnjoySport Example

19 EnjoySport Example

20 Limitations of Candidate Elimination
Training data contains errors Target concept is not in H, it can not be described in current hypothesis representation

21 Partially learned concept

22 Inductive Bias

23 Inductive learners modeled by equivalent deductive systems


Download ppt "IES 511 Machine Learning Dr. Türker İnce (Lecture notes by Prof. T. M"

Similar presentations


Ads by Google