The goal of this repository is to support projects that use Python, AI, and Machine Learning.
You can access a self-paced image-processing-based introduction to AI and Machine Learning through my guided tutorial
For more advanced work, refer to the Google Colab notebooks developed for Hands-On Machine Learning with Scikit-Learn and PyTorch: Concepts, Tools, and Techniques to Build Intelligent Systems by Aurélien Géron.
To install the tutorials locally on your machine, execute:
Follow the installation instructions.
If you have trouble with the torchvision installation, you may want to consult the link:
conda config --add channels conda-forge conda config --set channel_priority strict conda install torchvision
This material is covered in Conda trips and tricks
Here is a screen dump of my successful installation based on anaconda prompt.
His book titled Hands-on Machine Learning with Scikit-Learn and Pytorch: Concepts, Tools, and Techniques To... Build Intelligent Systems can be accessed for free through UNM library links to O'Reilly books, IEEE, etc
The original Scikit-Learn website has outstanding tutorials for Machine Learning. They can be found at Scikit Learn website.
Similarly, the official PyTorch website is a great place to start.
Refer to my guide on how to mount datasets using Google Drive and how to test official PyTorch tutorials based on my Colab guide for PyTorch
How to learn more about Machine Learning and Statistical Learning theory using other recommended books
For the statistical foundations of AI and Machine Learning methods, I use An Introduction to Statistical Learning. You can download the PDF of the book for free. The accompanying Python labs are excellent and demonstrate several essential concepts.
An accessible reference to modern AI/ML concepts can be found in Deep Learning: Foundations and Concepts. The book is freely available online.
One of my students found the Understanding Deep Learning book by Simon J.D. Prince to be highly accessible. This book can be accessed from GitHub link.
At UNM, you can openly access the book by Professor Martínez-Ramón who teaches our Deep Learning course. His book, co-authored with UNM students alumni, is titled at Deep learning : a practical introduction / Manel Martínez-Ramón, Meenu Ajith, Aswathy Rajendra Kurup. You can access it through link. If the link does not work, search for it through the UNM library link.
The following textbook contains simple explanations to many essential concepts:
Machine Learning Q and AI by Sebastian Raschka.
It is available at Oreilly link.
For UNM students, it is available for free through UNM library links to O'Reilly books, IEEE, etc.
Requirements for project proposals, midterm presentations, and final presentations can be found in project assignments webpage. This readme file contains how-to tutorials to help you develop your project. Example projects are given at the end of this document.
To create your own repo refer to the GitHub guide.
In order to develop Google Colab tutorials for your own repo, refer to Google Colab tutorial for repos.
- Special GitHub for Medical image and video analysis projects (including regular images and videos)
- Special GitHub for PyTorch model optimization.
- Search for Datasets on Google Dataset Search.
- Search for Papers with code. Look separately for Methods and Datasets.
- Search for datasets, models, and dataset competitions on kaggle.
- Search for Computer Vision datasets on PyTorch vision datasets website.
- Search for pretrained PyTorch models PyTorch models website.
- You can start with well-developed tutorials from PyTorch Hub.
Using VGGT and Affine Transformations on Point Clouds by Jason Wiberg
Within VGGT_Tutorial.ipynb you can learn to use VGGT to generate point clouds from images, and align the point clouds to specified coordinate systems that can correspond to real-world geometry. Then, you can also try to use generative AI models like Qwen-Image_edit-2509 and specialized Loras to generate images of a scene from different angles. Use the generated images to improve VGGT inference on the original image
GitHub
RF signal classification by Markus Parrish
This project presents the development and evaluation of machine learning models for identification of radio–frequency (RF) signals, with a focus on
Automatic Modulation Classification (AMC) using the RadioML 2016.10A dataset.
Tutorial: Automatic Modulation Classification Analysis of Traditional and Deep Learning Methods
Audio classification by Benjamin Metzner
This GitHub demonstrates the new required format for GitHub projects for ECE 551.
There are separate modules for data loading, training, and testing. Refer to
audio classification project based on separate modules
Video segmentation using SAM (complete) and SAM2 (incomplete) by Brian McCollum
This GitHub demonstrates the use of foundation models with FastAPI to provide ground truth.
It can be accessed through video segmentation project
Custom dataset for image classification by James Griego
This early GitHub provides essential information on how to build a
custom dataset for image classification using open datasets.
Custom dataset for 1000 handwritten digit images captured by Raphael Perea
This GitHub provides information on how to build a dataset based on your own images.
It can be accessed through
custom dataset based on 1000 handwritten digit images.
Mars image segmentation by Ary Naim
This GitHub provides an image segmentation example.
You can directly run the tutorial based on the Google drive link.