Toggle navigation sidebar
Toggle in-page Table of Contents
Introduction
to Machine Learning
Introduction to Machine Learning
About this course
Learning outcomes
Instructor & Schedule
JupyterHub for class
Evaluation
Week 1
1. Course Trailer
From detectors to publications
What is Machine Learning?
Which problems does ML solve?
2. Warm up: Linear Regression
Gradient Descent in 1D
Multivariate linear regression
Learning Rate
Gradient Descent in practice
3. Classification algorithms
Logistic Regression: introduction
What is the Sigmoid Function?
Cost Function for Classification
Regularization
Performance Metrics
4. Decision Trees and Boosting
What are Decision Trees?
Ensemble Learning and Random Forests
What is boosting?
5. Review Week 1
Week 2
6. Neural Networks Part I
Motivations
Model Representation
Activation Functions
Feedforward Propagation
7. Neural Networks Part II
Neural Network Loss Function
Initialization
Backpropagation Algorithm
8. Towards Deep Learning Models
Stochastic Gradient Descent
Varying the Learning Rate
Hyperparameters in DL
Let’s train our NN!
9. Convolutional Neural Networks
Learn CNNs
Guest Lecture
10. Review Week 2
Week 3
11. Unsupervised Learning Part I
Overview
k-Means Clustering
Dimensionality Reduction
12. Unsupervised Learning Part II
Autoencoders
Variational Autoencoder for Anomaly Detection
13. Big Data & ML Strategies
Big Data
Strategies in Machine Learning
14. Ethics in ML & Outlook
Ethics in ML
Outlook
15. Project presentations & Exam
Tutorials
1. Linear Regression in Python
2. ‘Forestree’ with LHC collisions
3. Classification Contest
4. Anomaly Detection
Index
