The mathematical description of deep learning has long been dominated by the language of algebra: matrices, gradients, and optimization landscapes. A parallel and perhaps more intuitive language howev

A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark

Computer Science Department at ETH Zurich. The department offers highest quality in computer science research and education and adds to business and industry growth.

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to mul...

In the world of machine learning and data science, cosine similarity has long been a go-to metric for measuring the semantic similarity between high-dimensional objects. However, a new study by resear...