Data Warehousing and Data Mining · Unit 4
Classification Techniques
Exam-focused notes for Classification Techniques (Data Warehousing and Data Mining, BIT454): what the TU syllabus asks and how it has actually been tested, with 3 solved past questions from this unit.
What this unit covers
- Classification by back propagation
- Bayesian classification methods
- Decision tree induction
- Gini index for attribute selection
- Support vector machines
- Lazy learners and instance-based learning
- Ensemble methods
Classification by back propagation
What do you understand by classification by back propagation? How is it different from Bayesian classification? Explain.[10]
Back Propagation is a supervised learning algorithm used to train artificial neural networks for classification tasks. 1. Network Structure: Uses a multi-layer feedforward neural network with an input layer, one or more hidden layers, and an output layer. 2...
Full solved answer →Gini index for attribute selection
How can you use Gini index as attribute selection algorithm? Illustrate with an example.Describe the working mechanism of support vector machine.[5+5]
(a) Gini Index as Attribute Selection Algorithm The Gini index (or Gini impurity) measures the probability of incorrectly classifying a randomly chosen element if it were randomly labeled according to the class distribution in a dataset. It is used in decis...
Full solved answer →Lazy learners and instance-based learning
Discuss about lazy learners and ensemble method. [5]
Definition: Lazy learners are machine learning algorithms that defer the learning process until a query (prediction request) is made. They store the entire training dataset and perform minimal processing during the training phase. Characteristics: - Minimal...
Full solved answer →Make Unit 4 stick
Practice BIT454 with flashcards & quizzes