You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
SC does not use tSNE, mostly because I'm afraid that it might be very slow, and requires fine hand parameter tuning, depending on the dataset. But this is something we could think of: to launch tSNE before the clustering, instead of a plain and naive PCA. Do you have in mind a special library/implementation?
True, but the hyper parameters are a problem if the number of spikes is really low (~ 100) with anything on the scale of thousands, the performance is robust to tuning of the parameters (e.g. perplexity between 5 to 50). Anyways, a good choice can be perplexity of 30 and learning rate of 500.
it is nice if SC provides the users with the option to choose tSNE instead of PCA (through a setting in the parameter file perhaps), at least for experimentation. The default can still be PCA.
can we have the option to choose the clustering algorithm to be applied on the tSNE space of the waveforms?
The text was updated successfully, but these errors were encountered: