UTMIST-MLF

Course materials for Machine Learning Fundamentals (MLF) — an 8-week curriculum from UTMIST covering core ML concepts through hands-on Jupyter notebooks.

Contents

Each week includes question notebooks for practice and answer notebooks for reference. Weeks 1–4 and 6–8 also include helper modules in utils.py.

Week	Topic
1	PyTorch fundamentals & linear regression
2	Logistic regression, model evaluation & autograd
3	Neural networks (foundations)
4	Neural networks (training & backpropagation)
5	Decision trees & random forests
6	Naive Bayes (text classification)
7	Convolutional neural networks (CIFAR-10)
8	Deep learning architectures (AlexNet, ResNet, LSTM, Transformers, ViT)

Getting Started

1. Clone the repository and open a week's notebook in Jupyter.
2. Install dependencies as needed (most notebooks include %pip install cells for packages like torch, numpy, matplotlib, and scikit-learn).
3. Work through the *_questions.ipynb notebooks; refer to *_answers.ipynb when stuck.