Closed kalfasyan closed 2 years ago
I haven't worked with time series but worked with some radar data that had a temporal dimension. Some techniques (the ones that propagate all the way back to input: integrated grads, guided backprop) are easily applicable while others (gradcam) are a bit tricky to get it right. You have to play around with the implementation to tune it to your model.
Would it be possible to handle networks trained for timeseries classification? Example CNN below: