FIND-S: FINDING A MAXIMALLY SPECIFIC HYPOTHESIS

-

 

FIND-S: FINDING A MAXIMALLY SPECIFIC HYPOTHESIS





•        To illustrate this algorithm, assume the learner is given the sequence of training examples from the EnjoySport task.


Step 1: Initialize h to the most specific hypothesis in H


FIND-S: Step-2








·       The first step of FIND-S is to initialize h to the most specific hypothesis in H

h - (Ø, Ø, Ø, Ø, Ø, Ø)

·       Consider the first training example

x1 = <Sunny, Warm, Normal, Strong, Warm, Same>, +

•        Observing the first training example, it is clear that hypothesis h is too specific. None of the "Ø" constraints in h are satisfied by this example, so each is replaced by the next more general constraint that fits the example

h1 = <Sunny, Warm, Normal, Strong, Warm, Same>

·       Consider the second training example

x2 = <Sunny, Warm, High, Strong, Warm, Same>, +

•        The second training example forces the algorithm to further generalize h, this time substituting a "?" in place of any attribute value in h that is not satisfied by the new example

h2 = <Sunny, Warm, ?, Strong, Warm, Same>

 ·       Consider the third training example

x3 = <Rainy, Cold, High, Strong, Warm, Change>, -

•        Upon encountering the third training the algorithm makes no change to h. The FIND-S algorithm simply ignores every negative example.

h3 = < Sunny Warm ? Strong Warm Same>

·       Consider the fourth training example

x4 = <Sunny Warm High Strong Cool Change>, +

•        The fourth example leads to a further generalization of h

h4 = < Sunny Warm ? Strong ? ? >

The key property of the FIND-S algorithm

·       FIND-S is guaranteed to output the most specific hypothesis within H that is consistent with the positive training examples

·       FIND-S algorithm’s final hypothesis will also be consistent with the negative examples provided the correct target concept is contained in H, and provided the training examples are correct.







Comments

Post a Comment

Popular posts from this blog

Machine Learning 1: UNIT 3 : Support Vector Machines MCQs

-
UNIT 3 Support Vector Machines MCQs  ----------------------------------------------------------------------------------------------------------------------------- 1. A Support Vector Machine can be used for A.     Performing linear or nonlinear classification B.     Performing regression C.     For outlier detection D.     All of the above Ans: D 2. The decision boundaries in a Support Vector machine is fully determined (or “supported”) by the instances located on the edge of the street? Top of Form True False Ans: A 3. Support Vector Machines are not sensitive to feature scaling A.     Top of Form True False Ans: B 4. If we strictly impose that all instances be off the street and on the right side, this is called  Soft margin classification  Hard margin classification  Strict margin classification  Loose margin classification Ans...
Machine Learning

Machine Learning MCQs-2 (Performance Metrics, Linear Regression, Naïve Bayes Classifier )

-
                               Machine Learning MCQs- 2 Performance Metrics, Linear Regression, Naïve Bayes Classifier  1.   The greater the value for ROC AUC, better the model: True False Ans: 1   2.   A set of data are all close to each other, and they are close to the actual value.  This set of data can be described as... Accurate Precise both Precise and accurate None of the above Ans: 3 3. The maximum value of the ROC AUC is: 0.8 0.9 1 0 Ans: 3 4. Recall can be increased by increasing the decision threshold. True or False? True False Ans: 2 5. Which of these is a good measure to decide which threshold to use? Confusion matrix F1 score ROC curve Precision & Recall versus Threshold Curve Ans: 4 6.  Which of these may have to be performed before analyzing and training the dataset? Shuffling Cross-Validation F1 Score None Ans: 1 7. For the below confusio...
Machine Learning

VERSION SPACES AND THE CANDIDATE-ELIMINATION ALGORITHM

-
Image
  VERSION SPACES AND THE CANDIDATE-ELIMINATION ALGORITHM   •         The key idea in the CANDIDATE-ELIMINATION algorithm is to output •         a description of the set of all hypotheses consistent with the training examples Note difference between definitions of consistent and satisfies ·        An example x is said to satisfy hypothesis h when h(x) = 1, regardless of whether x is a positive or negative example of the target concept . ·        An example x is said to consistent with hypothesis h iff h(x) = c(x) The LIST-THEN-ELIMINATION algorithm The LIST-THEN-ELIMINATE algorithm first initializes the version space to contain all hypotheses in H and then eliminates any hypothesis found inconsistent with any training example . ___________________________________________________________________________ 1. VersionSpace c...
Machine Learning