Time2Vec learns a vector representation of time that improves model performance when used in place of raw time inputs across various models and problems.
Fourier neural networks: An approach with sinusoidal activation functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Time2Vec: Learning a Vector Representation of Time
Time2Vec learns a vector representation of time that improves model performance when used in place of raw time inputs across various models and problems.