수학적 원리로 설명하는 기계학습(Mathematical principles in Machine Learning) Course introduction : edwith

수학적 원리로 설명하는 기계학습(Mathematical principles in Machine Learning)

Jason Lee 울산과학기술원(UNIST)

강의목록

Week 01
1. 1-1 Perceptron and its convergence theorem
1. 1-2 Maximum Margin Principle and Soft Margin Hard Margin
1. 1-3 Complexity of Linear Hypothesis and Margin Bound of Linear Classifiers
1. 1-4 Linear models in Deep Neural Networks
Week 02: Sparse modeling
1. 2-1 Overview of sparse modeling
1. 2-2 Matrix decomposition
1. 2-3 Regularized likelihood methods
Week 03: Causality
1. 3-1 Introduction to Causality
1. 3-2 Causal Bayesian Network
1. 3-3 Temporal Causality
1. 3-4 Counter-factual Inference
Week 04: Explainable AI
1. 4-1 Overview of Explainable AI
1. 4-2 Explaining decision of deep learning
1. 4-3 Explaining complex machine learning models by decomposition
1. 4-4 Featured research projects in Explainable AI
Week 05: Learning to learn
1. 5-1 Meta learning
1. 5-2 Few-shot learning
1. 5-3 Model-Agnostic Meta-Learning
1. 5-4 AutoML
Week 06: Methods to Predict the Future Values
1. 6-1 Time series prediction
1. 6-2 Stationarity of time series
1. 6-3 Non-stationary time series
1. 6-4 Deep learning-based model and recent development
Week 07: Reinforcement Learning: Self-Taught Artificial Intelligence
1. 7-1 What is the reinforcement learning?
1. 7-2 Approaches to reinforcement learning
1. 7-3 xample: GridWorld
1. 7-4 Example: CartPole