In this 3h tutorial, participants will be briefly introduced to (i) the idea of using neural networks to conduct classification, (ii) practical experience of creating a neural network model using available torch modules in R, (iii) the configuration of hyperparameters of neural networks and their influence on the model performance, and (iv) overfitting issue.  This tutorial focuses on the basic ideas of neural networks and does not involve mathematics derivation heavily.  

At the end of the workshop, participants will be able to: 
- Understand the general pipeline of conducting classification, and the concept of activation function and loss function. 
- Understand the concept of hyperparameters 
- Understand the concept of overfitting

Prerequisites 
- Understand the classification problem and the general pipeline of conducting prediction, including the training, and testing procedure; e.g. from workshops Introduction to ML in R, or Fundamentals of ML in Python. 
- Knowledge of the basics of regression is preferred.  
- Knowledge of R and RStudio. 
- Install R and RStudio on your computer. You can find installation instructions here. Please contact us (cdsi.science@mcgill.ca) if you are having trouble with installation.
- You need to bring your own laptop for this workshop. Contact us if you would like to attend but it's impossible for you to bring a laptop.

Location: HYBRID. Online via Zoom, or in-person at Burnside Hall room 1104 (11th floor).
Instructor: Qihuang Zhang, assistant professor of Epidemiology, Biostatistics, and Occupational Health (EBOH) at McGill University.