Draft:Two-tower model

In machine learning and recommender systems, a two-tower model is a neural network architecture that combines learned vector embeddings of users and items into a similarity measure.


 * https://hackernoon.com/understanding-the-two-tower-model-in-personalized-recommendation-systems
 * https://cloud.google.com/blog/products/ai-machine-learning/scaling-deep-retrieval-tensorflow-two-towers-architecture
 * https://www.hopsworks.ai/dictionary/two-tower-embedding-model