Meeting Minutes === ###### tags: `AI` `Meeting` `Salting` `CDMS` `AI/ML` `ML` `ML/AI` `salting` :::info - **Location:** https://ucdenver.zoom.us/j/97994358165 - **Date:** June 29, 2023, 10 AM Mountain - **Participants:** - Amy Roberts (AR) - - **Meeting Goal(s)** ::: ## Summary <!-- Please fill me in after the meeting --> - Aditi will be talking about her work! https://confluence.slac.stanford.edu/display/CDMS/CDMSLite+Run+3+%28re-%29analysis+using+NxM+filter 11 AM Pacific Wednesday July 5th ## Notes <!-- Other important details discussed during the meeting can be entered here. --> - All the pulses generated by the GAN look the same! Farnoush: that may be what we expect because we're normalizing the input pulses. It may be tricky to convince the GAN to keep the noise. - Mithun has found a nice resource explaining some of the TimeGAN parameters. TimeGAN has a sliding window it uses to sample the data: https://towardsdatascience.com/modeling-and-generating-time-series-data-using-timegan-29c00804f54d. Farnoush thinks that the example on this webpage is probably an example of a single event and that the data consists of many events of this shape.