This is an accordion element with a series of buttons that open and close related content panels.
Course Outline
Module 1: Introduction to AI & ML Problems
- Data representation and key features of ML pipelines
- Data acquisition and preprocessing example
- Supervised and unsupervised Learning
- Classification and regression problems
- Dimension reduction and clustering problems
- Examples of machine learning approaches
Module 2: Models for Supervised Learning
- Supervised learning review
- Linear models
- Nonlinear models
- Neural network principles
Module 3: Training Models and Performance Estimation
- Supervised learning and machine learning models review
- Model selection and performance analysis
- Gradient based optimization methods
- Methods for controlling model overfitting
- Criteria for optimization of classification models
- Multiclass classification criteria
- Backpropagation for training neural networks
Module 4: Clustering and Dimension Reduction
- Unsupervised learning review
- Clustering methods
- Dimensionality reduction, information extraction, and noise reduction