Group assignment 1

Portfolio Exercise 1:

Introduction

Task

• Build, train, and evaluate a neural network with Pytorch.
• It should have minimum 2 hidden layers
• Experiment with at least 5 different variations of hyperparameters (n layers / neurons, activation function, epochs, optimizers, learning rate etc.).
• Use gradio to build a simple interactive demo (in the notebook).

This should include:

1. Feature selection
2. Feature engineering (if necessary)
3. Standard ML preprocessing (if necessary)
4. Train-test split.
5. Defining a neural network architecture in putorch
6. Define a training loop.
7. training the model.
8. Try out different hyperparameters.
9. Evaluate the final model on the test data.
10. Visualize results with Grad.io

Data

• Self choosen dataset from the M1 module last semester.

Delivery

• Create a github repository
• Save colab notebook in the github.
• Provide a readme.md with brief description.
• Submission can be in groups up to 3.
• Submit by sending an email with link to repo to Hamid (hamidb@business.aau.dk) with Daniel & Roman in cc. (dsh@…, roman@…)