Meeting Minutes
===

###### tags: `AI` `Meeting` `Salting` `AI/ML` `ML` `ML/AI` `CDMS`

:::info
- **Location:**
- **Date:** Sept 21, 2023, 10 AM Mountain
- **Participants:**
- Amy Roberts (AR)
-
- **Meeting Goal(s)**

:::

## Summary
<!-- Please fill me in after the meeting -->
- Farnoush will send Zack a survey on incorporating physics into the model and Zack will return with a summary

## Notes
<!-- Other important details discussed during the meeting can be entered here. -->
- Zack is picking up Mithun's work and is doing part of the work to push the data through CDMSBats
- Sukee has updates to her work on classifying low-frequency noise for CDMSlite!
- There's a lot of dependence on the baseline of the pulse
- Farnoush suggests (and Sukee has looked at) deliberately moving the baseline. It sounds like the model is latching onto an unimportant feature for the classification.
- Farnoush wonders if LSTM might help introduce features that *are* important
- https://github.com/topics/cnn-bilstm
- Amy is wondering if it's possible that the baseline really could correlate with noise?