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
Hi @thomasp85 thanks for this super nice package!
I hope it is appropriate to ask a quick question here.?
Does your implementation already support explainers for time series recurrent neuronal networks?
I am a bit new to keras and lime in R. But this usecase would make it quite attractive to dive a bit deeper into this.
The text was updated successfully, but these errors were encountered:
Hi @Tazinho! The M in lime stands for 'model_agnostic', so theoretically all models are supported. What you problaby have to do is to implement methods predict_model.your_model_name and model_type.your_model_name to make it work. Check out how it's done in models.R.
If you need support for image, this is currently work in progress.
Right now Lime is good at classification task. You will also need to formulate the prediction in a way which match the Lime spirit. As said by @expectopatronum it s model agnostic.
Hi @thomasp85 thanks for this super nice package!
I hope it is appropriate to ask a quick question here.?
Does your implementation already support explainers for time series recurrent neuronal networks?
I am a bit new to keras and lime in R. But this usecase would make it quite attractive to dive a bit deeper into this.
The text was updated successfully, but these errors were encountered: