Special Topics

Topics

• Math/Notation/Definitions.
• ML algorithms 1 (linear and logistic regression).
• ML algorithms 2 (decision trees).
• ML algorithms 3 (support vector machines and K-Nearest neighbour).
• learning algorithm).
• Feature engineering, learning algorithm selection, Train/Test/Validation sets
• under-fitting, over-fitting, regularization.
• Model performance assessment, hyperparameter tuning/cross-validation.
• Neural networks (multi-layer feed-forward networks, backpropagation).
• Deep learning (convolutional neural networks, recurrent neural networks).
• Problems & solutions (e.g. Kernel regression, multiclass classification, one-class
• classification, multi-label classification, ensemble learning, label sequences
• sequence-to-sequence learning, active learning, semi-supervised learning, one
• shot learning, zero-shot learning).
• Advanced practice (class imbalance, combining classifiers, algorithm efficiency
• training neural networks, encoding input data, regularization, multiple inputs &
• outputs, transfer learning).
• Density estimation, clustering.
• Dimensionality reduction, outlier detection.
• Metric learning, learning to rank, learning to recommend, denoising auto