High-Performance Implementation of Spectral Learning of Latent-Variable PCFGs (Cohen et al., 2013)
- Updated
- Python
![]() |
VOOZH | about |
High-Performance Implementation of Spectral Learning of Latent-Variable PCFGs (Cohen et al., 2013)
A Python package implementing Rectified Spectral Units (ReSUs), a biologically inspired neural building block for backprop-free training using spectral decomposition and Canonical Correlation Analysis (CCA).
Code for "Automata in Space: Formal Language Theory meets Neural Computation"
Simple spectral learning for weighted automata
Add a description, image, and links to the spectral-learning topic page so that developers can more easily learn about it.
To associate your repository with the spectral-learning topic, visit your repo's landing page and select "manage topics."