Resources
Open Machine Learning Textbooks, Software, and Datasets
This course relies exclusively on Open Educational Resources (OER). All materials listed below are free to read, download, and reuse, and many include executable code and real datasets. Students are encouraged to return to these resources throughout the semester and beyond.
Open Textbooks
Required
An Introduction to Statistical Learning (ISLP)
Why required: Core intuition behind standard ML algorithms.
- PDF (official): https://www.statlearning.com
- Python labs/code: https://github.com/intro-stat-learning/ISLP
Used in: regression, classification, model evaluation.
Dive Into Deep Learning (D2L)
Why required: Interactive deep learning text with runnable code.
- Online interactive book: https://d2l.ai
- PDF: https://d2l.ai/d2l-en.pdf
- Code notebooks: https://github.com/d2l-ai/d2l-en
Used in: neural networks, deep learning labs.
Recommended
Mathematics for Machine Learning
Why recommended: Mathematical foundations behind ML.
- PDF: https://mml-book.github.io/book/mml-book.pdf
- Companion site: https://mml-book.github.io
Use when you need help with linear algebra, calculus, or probability.
Probabilistic Machine Learning
Why recommended: Deeper theoretical understanding of uncertainty.
- Free draft: https://probml.github.io/pml-book/book1.html
Optional reading for advanced or curious students.
Open Software & Tools (Required)
All software is open-source and free.
Programming Language
Core Libraries
- NumPy: https://numpy.org
- Pandas: https://pandas.pydata.org
- Scikit-learn: https://scikit-learn.org
- Matplotlib: https://matplotlib.org
Deep Learning Frameworks
- PyTorch: https://pytorch.org
- TensorFlow / Keras: https://www.tensorflow.org
Open Datasets
Required Repositories
- UCI Machine Learning Repository
https://archive.ics.uci.edu/ml - OpenML
https://www.openml.org - NYC Open Data
https://opendata.cityofnewyork.us
Used in labs, assignments, and final projects.
Recommended
- Kaggle Open Datasets
https://www.kaggle.com/datasets
(Only datasets with open licenses may be used.)
Open Research & Reference
Recommended
- Journal of Machine Learning Research (JMLR)
https://www.jmlr.org - arXiv (Machine Learning & AI)
https://arxiv.org/list/cs.LG/recent
https://arxiv.org/list/stat.ML/recent
Used for project inspiration and exposure to current research.
How to Use These Resources (Student Guide)
What You Must Read
- ISLP chapters assigned weekly
- D2L chapters for neural networks
What You Must Install
- Python
- NumPy, Pandas, Scikit-learn
- PyTorch or TensorFlow
What You Must Use
- Open datasets from UCI, OpenML, or NYC Open Data
What Is Optional
- Math for Machine Learning (for review)
- Probabilistic ML (for deeper theory)
- Research papers (for projects)
Open Education Reminder
All required course materials are:
- Free of cost
- Legal to download
- Reusable under open licenses
You are encouraged to keep copies, reuse code, and cite sources properly.
