Knowledge Base Resources

This workshop focuses on developing an understanding of the fundamentals of attention and the transformer architecture so that you can understand how LLMs work and use them in your own projects.

This workshop series introduces the essential concepts in deep learning and walks through the common steps in a deep learning workflow from data loading and preprocessing to training and model evaluation. Throughout the sessions, students participate in writing and executing simple deep learning programs using Pytorch – a popular Python library for developing, training, and deploying deep learning models.

This is a very barebones introduction to the PyTorch framework used to implement machine learning. This tutorial implements a feed-forward neural network and is taught completely asynchronously through Stanford University. A good start after learning the theory behind feed-forward neural networks.

This tutorial series and documentation covers topics on using Python on HPC clusters. The specific steps are based on the HOPPER cluster at George Mason University in Fairfax, VA. They should be implementable on most HPC clusters that have the SLURM scheduler installed, the Environment Modules system for managing packages and Open onDemand for a web-based GUI to access the cluster resources.

Numpy is a python package that leverages types and compiled C code to make many math operations in Python efficient. It is especially useful for matrix manipulation and operations.

HPCwire is a prominent news and information source for the HPC community. Their website offers articles, analysis, and reports on HPC technologies, applications, and industry trends.

A walkthrough (with a Google Colab link) on how to implement your own LSTM to observe time-dependent behavior.

This tutorial is essentially the "hello world" of image recognition and feed-forward neural network (using PyTorch). Using the MNIST database (filled within images of handwritten digits), the tutorial will instruct how to build a feed-forward neural network that can recognize handwritten digits. A solid understanding of feed-forward and back-propagation is recommended.

Fastai offers many tools to people working with machine learning and artifical intelligence including tutorials on PyTorch in addition to their own library built on PyTorch, news articles, and other resources to dive into this realm.

The official documentation for PyTorch, a machine learning tensor-based framework, and NumPy, which allows for support for ndarrays which is useful to make tensors when implementing NNs. Both libraries can be installed with pip.

DeepChem is an open-source library built on TensorFlow and PyTorch. It is helpful in applying machine learning algorithms to molecular data.