Supervised and Unsupervised Learning .pptx

Supervised and Unsupervised Learning Algorithm

1. SUPERVISED AND UNSUPERVISED LEARNING TECHNIQUES -Ms. Keren Evangeline. I / AP(O.G) SRM Valliammai Engineering College Department of Medical Electronics Faculty Development Programme

2. LIST OF COMMON UNSUPERVISED ML MODELS K – Means Clustering Principal component analysis (Dimensionality Reduction) Hierarchial clustering

3. ADVANTAGES OF UNSUPERVISED ML MODELS

4. DISADVANTAGES OF UNSUPERVISED ML MODELS

5. DECISION TREE

6. [Size < 2000?] / \ Yes (<=2000) No (>2000) / \ [Bedrooms < 3?] [Lot Size < 5000 sq.ft ?] / \ / \ Yes (<=3) No (>3) Yes (<5000) No (>5000) / \ / \ [Year < 1990?] [Price: $400K] [Price: $450K] [Price:$550K] / \ Yes No / \ [Price: $300K] [Price: $350K] Continuous Variable Decision Tree

7. RANDOM FOREST

8. Introduction A random Forest Algorithm is a supervised machine learning Algorithm consisting decision trees.  The general method of random decision forests was first proposed by Ho in 1995. After that, It was developed by Leo Breiman in 2001. RANDOM FOREST 33

9. Decision Tree Random forest 34

10. Decision Tree – Important Terms Random forest 35

11. How Decision Tree Works It follows a tree-like model of decisions and their possible consequences.  The algorithm works by recursively splitting the data into subsets based on the most significant feature at each node of the tree. Random forest 36

12. How Decision Tree Works Random forest 37

13. Ensemble Learning      Ensemble learning creates a stronger model by aggregating the predictions of multiple weak models. Random Forest is an example of ensemble learning where each model is a decision tree. The idea behind it is- the wisdom of the crowd. The majority vote aggregation can have better accuracy than the individual models. Random  forest 38

14. Dataset Preparation     Bootstrap Aggregating (Bagging)    Creating a different training subset randomly from the original training dataset with replacement is called Bagging. With replacement refers to the bootstrap sample having duplicate elements. Reduces variance, helps to avoid overfitting.    Out Of Bag (OOB)    The out-of-bag dataset represents the remaining elements which were not in the bootstrap dataset. Used for cross validation or to evaluate the performance.     Random Subspace Method(Feature Bagging)    While building the tree, for splitting, a randomly selected subset of the features are used. So, the trees are more different having low correlation.  Random forest 39

15. Bagging at training time​ Random forest 40

16. Bagging at inference time Random forest 41

17. Random Subspace Method at training time Random forest 42

18. Random Subspace Method at inference time Random forest 43

19. Definition The Random Forest algorithm is an ensemble learning method consisting of many decision trees that are built by using bagging and feature bagging which helps to create an uncorrelated forest of trees whose combined prediction is more accurate than that of a single tree. For classification tasks, final prediction is done by taking majority votes and for regression tasks, average of all the individual trees.  Random forest 44

20. Random Forest Model Random forest 45

21. Why Use Random Forest Random forests are an effective tool in prediction. Forests give results competitive with boosting and adaptive bagging, yet do not progressively change the training set. Random inputs and random features produce good results in classification- less so in regression. For larger data sets, we can gain accuracy by combining random features with boosting. Random forest 46

22. Advantages Versatile uses Easy-to-understand hyperparameters Classifier doesn't overfit with enough trees Disadvantages Increased accuracy requires more trees More trees slow down model Can’t describe relationships within data Advantages and Disadvantages

23. Random  Forest Applications Detects reliable debtors and potential fraudsters in finance Verifies medicine components and patient data in healthcare Gauges whether customers will like products in e-commerce Random forest 48

24. Thank you Any Question? Random forest 49