Representation Learning
A subfield of machine learning that enables models to automatically learn to transform raw data into high-dimensional feature vectors, such that similar samples are positioned closer together in the feature space. It is considered a core concept underlying deep learning.
Timeline (last 90 days)
Equivariance is a core concept in geometry and representation learning: if applying some transformation to the input causes the output to transform accordingly in a predictable way, the mapping is said to be equivariant to that transformation.
The basic idea of embedding vectors is to map high-dimensional, discrete, or hard-to-compute objects into low-dimensional continuous dense vectors, so that semantically or visually similar objects are closer in vector space.
All Facts (2)
Equivariance is a core concept in geometry and representation learning: if applying some transformation to the input causes the output to transform accordingly in a predictable way, the mapping is said to be equivariant to that transformation.
50%UnverifiedThe basic idea of embedding vectors is to map high-dimensional, discrete, or hard-to-compute objects into low-dimensional continuous dense vectors, so that semantically or visually similar objects are closer in vector space.
50%