minhnguyen-cs / mtsne Goto Github PK

can you please provide the dataset details

Hi @minhnguyen-cs ,

Thanks for sharing this code. I read the paper and am a little confused about few points. It would be great if you can help me in understanding the following points.

1. The ATOM-HP dataset experiment looks like a case of normal clustering and not time series since you are treating all the points independently of time dimension. Is this understanding correct?

2. What is the intuition behind m-TSNE working better than a DTW based approach. Do you think m-TSNE which uses EROS distance AND warping would work better since warping is important in time-series?

Thanks

Is there an Opensource license available?