Artificial Intelligence Bootcamp
This course provides an overview of the field of Artificial Intelligence (AI) with emphasis on contemporary techniques, such as machine learning and deep learning, and their applications in many areas, including computer vision, natural language processing, and medical diagnosis.
Students will learn the basics of AI, machine learning, and deep learning, and interact with a large number of hands-on examples of applications of AI in numerous domains. The course will broaden the participants' view of the field of AI, allowing a better understanding of its foundations, risks, applications, and implications, and motivating students to learn more about the topic.
Session Length: Date/Time Coming Soon
Click Here to Register
Please note that each class will be recorded. The recordings will be available online for 30 days to ensure that participants can access them if they miss a class or want to review any of the sessions.
Length: One week of online sessions (Monday-Friday, 2 hours/day)
Instructor: Oge Marques, PhD
Tools and Resources:
Lectures and group discussions will take place live (synchronously) online (using WebEx, Zoom, or equivalent) on specified days and times.
Slides and supporting materials will be posted online.
Coding examples will be presented using Google Colaboratory.
Students should have Internet access and a Google account to access the Google Colab notebooks containing examples.
Outline and tentative schedule
The course will consist of 5 modules (of 2 hours each). Each module will have a combination of lecture, demos, and discussions, with ample opportunity for questions.
- Fundamentals of AI: history, techniques, applications
- Fundamentals of Machine Learning (ML) and Deep Learning (DL)
- Examples of latest developments in AI, ML and DL
- The Machine Learning workflow: from data acquisition to deployment of a solution
- Example of a ML workflow
- Neural Networks: fundamentals and examples (using TensorFlow playground or equivalent)
- Deep Learning architectures (CNNs, RNNs, and more): fundamentals and examples (using Google Colab notebooks)
- Transfer Learning
- Deep Learning examples in computer vision, natural language processing, and medical diagnosis.
- AI and DL beyond the code: adversarial examples, transparency, fairness, bias explainability (the “black box effect”), data sharing, model sharing,accountability, and more.
- Where to go from here: suggestions of courses to take at FAU, books,newsletters, YouTube channels, podcasts, and other resources.
Click Here to Register