How do Twins and Triplet Neural Network work

Author(s): Edward Ma

Originally published on Towards AI.

Photo by Ralph Mayhew on Unsplash

As a practitioner, we usually build a multiclass classification model which is a predefined number of categories. Indeed, we do not need to know the total number of categories in both training time and inference time. Twins (aka Siamese) Network and Triplet Network are designed to support this scenario.

By feeding two inputs to Siamese Network, it determines the similarity between two inputs. For example, we can compare whether two images are in the same category. To be more precise, we can use it in zero-shot learning or few-shot learning in the meta-learning field. For Triplet… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI