機器學習

課程大綱

Introduction * Introduction to Machine Learning * Mathematical Foundations * Supervised Learning * Unsupervised Learning Learning Methods * ANN and Perceptron Algorithms * Logistic Regression * Support Vector Machines * Deep Learning Learning Scenarios * Transfer Learning, Domain Adaptation * Few-shot Learning * Continual Learning * Federated Learning * Semi-supervised Learning, Active learning, Self-supervised Learning * Anomaly Detection Dealing with Data Dependency * Sequential Data Learning * HMM, MRF, CRF * RNN, LSTM * Naïve Bayes * Probabilistic Graphical Models Generative Models and Multi-modalities * Discriminative vs. Generative Models * Transformers * LLMs and various foundation models * Diffusion Models * Learning with Multi-modalities