Syllabus

• Introduction:
  • Machine perception,
  • Recognition Cycle (sensing, segmentation, feature extraction, classification),
  • Teaching a computer to learn concepts using data
• Classification Problem
  • Classifier Model
  • Features: Feature Selection and Extraction
  • Linear Classifiers (Linear Discrimination)
• Learning from Data: Supervised vis-à-vis Unsupervised Learning
  • Statistical Learning
  • Working with Missing and Noisy Data
  • Bayesian Belief Networks
  • Parameter Estimation
  • Maximum Likelihood
  • Gaussian Parameter Estimation
  • Dimensionality Problem
• Unsupervised Learning
  • K-Means Clustering
• Decision Trees
  • Applications and Limitations
  • Optimizing Decision Trees
• Neural Networks:
  • Biological Inspiration
  • Structure
  • Applications
  • Learning
  • Neural Network Types
    • Multi-layer Neural Networks
    • Hebbian Networks
    • Hopfield Network
• Introduction to Deep Neural Networks
  • Convolutiona Neural Networks
  • Generative-Adverserial Networks
  • Auto-encoders
• Generalization
  • Overfitting Problem
  • Early Stopping
  • Regularization
• Support Vector Machines (SVM)
  • Linear SVM
  • Kernel-based SVM