Feature learning
In machine learning, feature learning or representation learning[2] is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.
Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data have not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms.
Feature learning can be either supervised, unsupervised or self-supervised.
Dynamic Representation Learning[edit]
Dynamic representation learning methods[49] generate latent embeddings for dynamic systems such as dynamic networks. Since particular distance functions are invariant under particular linear transformations, different sets of embedding vectors can actually represent the same/similar information. Therefore, for a dynamic system, a temporal difference in its embeddings may be explained by misalignment of embeddings due to arbitrary transformations and/or actual changes in the system.[50] Therefore, generally speaking, temporal embeddings learned via dynamic representation learning methods should be inspected for any spurious changes and be aligned before consequent dynamic analyses.