picard
picard copied to clipboard
Preconditioned ICA for Real Data
In the README, it says the following about the Picard settings: ``` ortho=False, extended=False: same solution as Infomax ortho=False, extended=True: same solution as extended-Infomax ortho=True, extended=True: same solution as FastICA...
For my current project I'm using matlab so it's a bit easier to use the matlab implementation of picard. While the `extended` option is clearly visible for the python picard...
This PR adds a 'll_reject' parameter. During the iterations, each sample with a negative log likelihood > ll_reject is going to be rejected. This helps finding artifacts.
python-picard fails with NumPy 2.x due to numerical overflow errors in `scipy.linalg.expm` during the optimization process. ### Environment - **python-picard**: 0.8.1 (also tested 0.8) - **NumPy**: 2.2.6 (also tested 2.2.4)...
Bumps the actions group with 1 update: [actions/checkout](https://github.com/actions/checkout). Updates `actions/checkout` from 2 to 6 Release notes Sourced from actions/checkout's releases. v6.0.0 What's Changed Update README to include Node.js 24 support...