Python for Machine Learning

0.25-3 Credits · Level: Graduate

This course will provide students with a hands-on introduction to the concepts and code behind machine learning systems. It will be divided into three modules. In the first module, we will cover some foundational concepts in data science and a basic introduction to coding in Python. In the second module, we will discuss several major machine learning algorithms and their applications. We will cover supervised and unsupervised learning, along with the steps to building a model, including data selection, pre-processing, training, evaluation, and deployment. In the third module, we will move onto neural network-based machine learning. We will branch into specific use cases, such as large language models and computer vision. Throughout the course, we will also introduce tools and techniques that are crucial to using machine learning in an enterprise setting, including GitHub, KFP, TFX, and cloud concepts. The objective of the course will be for students to develop a project portfolio demonstrating their proficiency in Python, through a combination of group and individual work. They will finish the course with an understanding of capabilities of AI systems, choosing models for specific use cases, ethics and bias in AI. They will have an understanding of what the entire development process of an AI system looks like from a Jupyter notebook to a deployed system, and the work it takes to get there.