search

ragulpr / wtte-rnn

WTTE-RNN a framework for churn and time to event prediction
MIT License
762 stars 186 forks source link

Why do you use a log in the discrete weibull loss function? #69

Closed agoblet closed 4 years ago

agoblet commented 4 years ago

In your Weibull discrete loss function, you use the K.log function: https://github.com/ragulpr/wtte-rnn/blob/master/python/wtte/wtte.py#L164

When looking at your thesis on page 45, where the log losses are defined, i don't see any log in the formula: https://ragulpr.github.io/assets/draft_master_thesis_martinsson_egil_wtte_rnn_2016.pdf

Why is the discrete loss implemented in that way?

Thanks a lot in advance.