-
I just wrote a CSP class which can be used as a scikit-learn estimator. I think it would be nice if we replaced the existing implementation with the new one, because that way CSP can be used in a broa…
cbrnr updated
8 years ago
-
As discussed at https://github.com/scot-dev/scot/issues/64, MNE's implementation of CSP consists of several steps (basically two times PCA using `linalg.eigh`). In contrast, SCoT directly computes CSP…
cbrnr updated
8 years ago
-
I am analysing a dataset 'qaaf' (attached) using logistic regression analysis.
The dataset includes:
1. speaker: participants in my study
2. item: words as used by my participants
3. realisation: the…
-
from @alanedelman:
We really should think carefully about how the transpose of a vector should dispatch the various `A_*op*_B*` methods. It must be possible to avoid new types and ugly mathematics. F…
-
Running SciPy's `linalg.eigh` on multiple machines yields results different from the correct ones by `linalg.eig`. Simple code to reproduce this is, in Python 3.4
``` python
import numpy as np
from s…
-
I stumbled upon a generalized eigenvalue problem where `linalg.eig` returns complex eigenvalues and `linalg.eigh` raises an exception:
```
numpy.linalg.linalg.LinAlgError: the leading minor of order …
cbrnr updated
9 years ago
-
are the eigenvectors of tICA intended to be orthogonal?
I get a non-zero dot product around 0.06:
```
a=np.array(tica_obj.eigenvectors)
np.dot(a[:,0]/np.linalg.norm(a[:,0]),a[:,1]/np.linalg.norm(a[:…
-
The generalized eigenvalue problem can be expressed as
A_x = k_B*x,
where k is the eigenvalue, x is the solution vector, matrix A and B correspond two sets of kernels.
There are essentially two eigen…
-
Having thought about the time-lagged data problem, I suggest the following change with respect to your latest TICA fix:
- X runs always through all data, even if no time-lagged data (Y) is available d…
-