From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 25,500 courses taught by industry experts.

ML model sources and deployment types

ML model sources and deployment types - Amazon Web Services (AWS) Tutorial

From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Start my 1-month free trial Buy for my team

ML model sources and deployment types

“

- There are different possible sources for ML models, and if we use an example like SageMaker in AWS, we have choices of open source, pre-trained or custom models. And open source pre-trained can include examples like models from Meta, Hugging Face, or TensorFlow. Custom models are built into the service with different algorithm choices, and so here are some examples of those algorithm choices, such as supervised learning, and we have some subclassifications in here, like regression. We have unsupervised learning, where we can do things like clustering or pattern recognition. We have image processing, which is pretty self-explanatory, object detection, computer vision, and that sort of thing. And finally, we have text analysis, which then spreads out into a wide range of use cases, whether we're doing document summarization, language transcription, or translation, and those sorts of actions. Now, as far as model deployments are concerned, there's a couple of different ways we can do…

Contents