After an initial introduction to the Python programming environment, instructions are provided to use Visual Studio Code as the workspace to visualize/write/execute Python code, and to take advantage of the Copilot autocoding tools provided by OpenAI/Github.
Topics:
- Introduction to Python programming
- Foundations of Linear Algebra
- Using PyTorch to implement deep neural networks (NNs) for both Classification and Regression using tabulated data and/or images.
- Transformers and Large Language Models (LLMs). This section focuses on the latest trends in natural language processing and explains how attention mechanisms help with modeling complex relationships in long sentences. In particular, this section describes state-of-the-art transformer models such as GPT.
- Graph Neural Networks (GNNs). This section goes beyond working with tabular datasets, images, and text. It introduces specialized neural networks that operate on graph-structured data. Examples of GNNs for node and graph classification, link prediction, dimensionality reduction, and for the generation of new graph objects (i.e., new drug molecules) will be presented.
- Knowledge Graphs (KGs). This section focuses on specialized heterogeneous graphs used to build searchable databases in the Neo4j format.