From the course: Cloud-Based AI Solution Design Patterns
Join today to access over 24,800 courses taught by industry experts.
Model-centric design patterns overview
From the course: Cloud-Based AI Solution Design Patterns
Model-centric design patterns overview
- There are a number of moving parts within an AI system, each of which can demand its own processing power and its own monitoring. There are data pre-processing and post-processing tasks that occur that don't necessarily involve the model, but which can require substantial compute power. However, it is the model that represents the AI system's inference logic, and the AI system is responsible for executing this logic to provide output results, which is how an AI system provides us with value. Therefore, this chapter covers a set of patterns dedicated to leveraging cloud environments and resources in support of AI model training and monitoring, as well as how a model can be collaboratively developed. Note that these model-centric patterns are further supplemented by two more model-centric patterns located in chapter three, specifically the containerized AI model deployment and serverless AI inference patterns that are more focused on the performance of a model as part of a greater AI…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.