Final Exam: (Time: 9:00 - 12:00, 17 April 2026, Friday; Location: Building 315/Room 216)

The final is based on:

• All the Lectures.
• Labs 1 to A
• Assignments 1 to 5

Topics included:

• Introduction
• Data
  • Why is it important to understand the data collection?
  • Attribute types (and later, how they affect the learning algorithms)
  • Common issues and how they are handled: missing values, noisy data
  • Data aggregation, reduction and transformation
• Information Based Learning
  • product: decision tree
  • how to build it: recursive algorithm, greedy algorithm
  • information in "information based": entropy, GINI, mis-classification rate
  • how to use it
  • issues (and how to handle them)
    • bad split situation (use information gain ratio instead of information gain)
    • overfitting (pre-pruning, post-pruning)
    • continuous descriptive attribute (discretization - equal width, equal depth, information based)
    • continuous target attribute (regression tree - using variance instead of entropy)
  • model ensembles (decision forest instead of tree)
• Similarity Based Learning
  • feature space (data format)
  • similarity (distance) metrics
  • how to use it: nearest neighbor algorithm
  • issues (and how to handle them)
    • noisy data (K nearest neighbor algorithm)
    • feature difference (normalization)
    • continuous target attribute (average instead of class label)
    • too many descriptive attributes (dimension reduction)
  • improve efficiency - indexing (such as K-D tree), pre-screening
• Probability Based Learning
  • some statistics concepts
  • how to get the probabilities
  • Bayes' Theorem
  • how to use probability based classifier in general?
  • Naive Bayes' classifier, and its BIG assumption
  • Bayesian Belief Networks
    • what does it look like?
    • Markov blanket
    • how to use it?
    • how to build it?
  • issues (and how to handle them)
    • insufficient data (smoothing)
    • continuous descriptive attribute (probability density function instead of a fixed set of probabilities)
    • missing parent attribute values - hidden variables (consider all possible values and their probabilities)
• Error Based Learning
  • multivariable linear regression
  • gradient descent algorithm
  • Artificial Neural networks (modelling non-linear functions)
    • Neuron model
    • Neuron Network model
    • Model applying (Forward propagation)
    • Model learning (Backward propagation)
  • issues (and how to handle them)
    • categorical target attribute (find the decision boundary)
    • non-linear relationships (use basis functions)
    • multinomial (instead of binary) output (multiple one-vs-all models)
    • computationally too expensive dot product operation (use kernel trick)
    • overfitting (stop training at an appropriate time)
• Classification Model Evaluation
  • statistical measurements based on the confusion matrix
  • Receiver Operating Characteristic Curve and ROC Index
  • Model Evaluation after Deployment
• Cluster Analysis
  • similarity based and density based
  • Clustering algorithms
    • Kmeans and its variants
    • Hierarchical clustering
    • Density-based clustering
  • Cluster Validity Evaluation
• Outlier Detection
  • Definition of Outlier
  • detection methods: graphical and statistical based; distance based; model based;
• Association Analysis
  • data format - market-basket model
  • find frequent itemsets
    • A-Priori algorithm, hash tree
    • tree projection
    • ECLAT, vertical database format
    • FP growth algorithm, FP-tree, conditional FP-tree
  • rule generation for A-Priori algorithm
  • Multiple Minimum Support and its effect on A-Priori algorithm
  • Association Rule Evaluation - objective statistical based measures (usually use contingency table) and subjective measures

Past exams: