Course Overview
In this course, you will explore the generative artificial intelligence (generative AI) application lifecycle, which includes the following:
- Defining a business use case
- Selecting a foundation model (FM)
- Improving the performance of an FM
- Evaluating the performance of an FM
- Deployment and its impact on business objectives
This course is a primer to generative AI courses, which dive deeper into concepts related to customizing an FM using prompt engineering, Retrieval Augmented Generation (RAG), and fine-tuning.
Welcome video
Video transcript
Developing generative AI solutions. Imagine being able to create stunning visuals, captivating stories, and even functional code with just a few prompts. Through the generative AI application lifecycle, we can train powerful models to generate human-like content across various domains. From generating personalized marketing campaigns to accelerating drug discovery, the possibilities are endless. Companies are already using this technology to automate content creation, reduce costs, and deliver truly unique experiences. With knowledge on developing generative AI solutions, you can unlock the full potential of generative AI to transform businesses and shape the future of content creation.
Learning objectives:
- Identify selection criteria to choose pre-trained models.
- Define Retrieval Augmented Generation (RAG) and describe its business application.
- Explain the cost trade-offs of various approaches to foundation model customization.
- Understand the role of agents in multistep tasks.
- Understand approaches to evaluate foundation model performance.
- Identify relevant metrics to assess foundation model performance.
Continue to the next lesson to explore the generative AI application lifecycle.