Revision 0f9ce693bda1e6591173af4de60a2cfa610f4957 authored by Marie Roald on 06 June 2021, 08:48:42 UTC, committed by Marie Roald on 06 June 2021, 08:48:42 UTC
Only making the constrained factor matrices non-negative seemed to make the fitting procedure less stable (higher likelihood of all-zero components).
1 parent 5f08046
CHANGELOG.md
# 0.4.0
- Added TensorFlow backend with Eager execution
- Added CuPy backend
- PyTorch backend updated for PyTorch >= '0.4.0'
# 0.3.0
- Added PyTorch backend
# 0.2.0
- Added MXNet backend
# 0.1.4
- Added Robust Tensor PCA
Computing file changes ...