For the vast majority of AI practitioners, there is little need to develop models from scratch! In most cases, there are models that have already been developed and can be reused either directly or with minimal modification for new tasks. Transfer learning is the process of taking a pretrained model and updating it to work in a new situation. Most AI applications involve some aspect of transfer learning. This course will introduce you to the basics of using transfer learning to harness the vast number of pretrained models. Using transfer learning reduces the amount of training data required, speeds up AI application development, and leverages prior work to move your project forward faster.
In this course, we’ll cover:
- Module 1: Transfer Learning Concepts
- Module 2: Implementing Transfer Learning Techniques
- Module 3: Evaluating and Optimizing Transfer Learning
Access content
| Link | Method of Access |
|---|---|
 |
Access in Practicum AI website. |
| Coming soon | Access on UF Professional and Workforce Development |
| Coming soon | Access on Canvas Commons |
 |
Access on GitHub.com |
 |
Access on Google Colab |
