Authors

Description

Machine learning is everywhere when using a mobile app: recommending people or products, detecting people or tags in an image, etc. Embeddings are an essential component when you need to obtain similarities with which it is possible to perform semantic searches, clustering, recommendations, anomaly detection, and classification, among others. Additionally, there are frameworks like MediaPipe that provide a set of libraries and tools to quickly apply machine learning (ML) to your applications. It is possible to use its SDK for multiple platforms, including Android, Python, and Web, to have ML in just a few minutes. In this talk we will talk about the use of embeddings, how to obtain them and what functions operate on them and all this in a very simple way with MediaPipe.