From the course: Introduction to AI-Native Vector Databases
Join today to access over 24,400 courses taught by industry experts.
Translating data from human to machine-understandable
From the course: Introduction to AI-Native Vector Databases
Translating data from human to machine-understandable
In the previous video, we discussed machine learning models that have the ability to translate data from human understandable format to machine understandable format, that is to say, into vectors. In this video, we'll dive deeper into how machine learning models understand our data. Classification machine learning models are trained to identify different classes of objects and images. They're shown millions of images and are optimized to predict the correct class of objects shown in all of these images. In order to recognize objects across all of these images, these ML models need to learn which features are common to a class, and thus can be used to distinguish that class from the others. So, for example, in identifying a stop sign, the model will have to learn to identify multiple visual features. Perhaps the color red, vertical, horizontal and diagonal edges, writing inside the sign, and et cetera. These visual features are each captured as numbers and contribute to determining the…
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.
