ToDo & Ideas - philippeller/freeDOM GitHub Wiki

Likelihood part

Large scale training
- use tf.data API for efficient transfers (done)
- current shuffling is extremely inefficient (done)
What MC to train on?
- L2, L7, …?
Semi-supervised training on data?
Try with Upgrade MC
Determine valid parameter ranges
Include info whether a pulse is HLC or SCL Reco pulses contain a flag, that we could input to the NN. The value of the flag in I3RecoPulse is the sum of:
```
1: icecube.dataclasses.PulseFlags.LC
2: icecube.dataclasses.PulseFlags.ATWD
4: icecube.dataclasses.PulseFlags.FADC
```
We may want two flags (that are 0 or 1), LC or not and ATWD vs. FADC. Pulse width is highly correlated with flag, but not 100%.
Include charge as training weights for pulses
Check output node bias, has very wild behaviour. maybe fix to 0...or maybe this is just the case as it is a single number
Should we add causality constraints? Or is it a bad idea given noise?
Could also limit parameter ranges in transformation layer, and do sqrt(r) etc

Goal: being able to reco ~10k events in one go, rather than a single event very fast, this would allow to evaluate the reco quality based on distributions
Minimizer strategy to allow for massive parallelization
- zmq client/server structure for likelihood computations?
Use available gradients?
for beginning, could use same minimizer as retro (spherical CRS), as it is a known part of the equation
What about actually sampling the posterior, now that we'd have a fast enough likelihhod?
Constraints from valid parameter ranges