Engineering AI Systems: Architecture and DevOps Essentials
by Len Bass, Qinghua Lu, Ingo Weber, Liming Zhu
3
AI Background
All [AI] models are wrong, but some are useful.
—George Box
. . . particularly LLMs.
—Ingo Weber
IN THIS CHAPTER, we introduce the foundational concepts of AI, with a particular emphasis on model selection and preparation required for training these models.
Models are ubiquitous in both science and engineering. But, as George Box noted, they are always inaccurate. The inaccuracy stems from the abstraction embodied in a model. Many details are not included in any model, and this lack of detail both facilitates reasoning about the behavior of the entity being modeled and serves as a cause of error. In an AI system, the choice of the AI techniques is one of the most important design decisions. It has a major influence on the quality ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access