Space-Time Local Embeddings Space-Time Local Embeddings
Paper summary The paper presents a data visualisation method based on the concept of space-time. The space-time representation is capable of showing a broader family of proximities than an Euclidean space with the same dimensionality. Based on the KL measure, the authors argue that the lower dimensional representation of the high dimensional data using the space-time local embedding method can keep more information than Euclidean embeddings. I am quite convinced, but there is one question about interpretability of the visualised data in space-time.

Summary by NIPS Conference Reviews 5 years ago
Your comment: allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and