From the course: Introduction to AI-Native Vector Databases
Join today to access over 24,800 courses taught by industry experts.
Machine learning models and object classification
From the course: Introduction to AI-Native Vector Databases
Machine learning models and object classification
We spoke earlier about translating from human-understandable data to machine-understandable data, or vectors, as we later called them. In this chapter, we'll explore how this translation happens. Vector databases use machine learning models to translate data into vector representations, such that as little meaning is lost in translation as possible. Most often, these models are neural networks. Machine-learning models can translate similar objects to vectors that are closer together in vector space, and dissimilar objects to vectors that are farther apart, thus retaining a lot of the meaning behind the vectors. How do machine learning models know where to locate each data point in vector space? This is best understood using an analogy. In a library books are placed in the correct location using the Dewey Decimal System. Depending on its topic, each book has an appropriate location in the library. Books on Latin grammar, for example, start with location number 475, while books about…
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.