Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Continual Learning for Sentence Representations Using Conceptors (2019, methodology): “To make the common discourse learned from one corpus more generalizable to another, we propose to use the conceptor matrix (Jaeger, 2017) to characterize and update the common discourse features in a sequence of training corpora.”
Continual Learning for Robotics (2019, methodology): “Conceptor are memory mechanism that store learned patterns and representation.”
Unsupervised Post-processing of Word Vectors via Conceptor Negation (2018, methodology): “Instead of discarding a fixed number of PCs, we softly filter word vectors using matrix conceptors (Jaeger 2014; 2017), which characterize the linear space of those word vector features having high variances – the features most contaminated by word frequencies according to Mu and Viswanath (2018).”