This repository contains introductory lectures on Machine Learning.
Lectures
- Basic concepts: This lecture gives an overview of basic concepts in machine learning (learning paradigms, training notions, illustration using the least-square problem)
- No deep Learning: This lecture contains examples of various non-deep learning models such as logistic regression, support vector machines, random forest, etc. The basic mathematical formulations and illustrative examples are given for each models.
- Intro to Deep Learning: This lecture gives an introduction to neural networks (the perceptron, the multi-layer perceptron, backpropagation, convolutional models, etc.). Once again, the basic mathematical formulations and illustrative examples are given for each concept.
- Intro to UNet/ResNet/DenseNet
- Advanced Deep Learning Concepts
Libraries: