How to Set Parameters Distribution For Bayesian Neural Network With PyMC3

Questions
2

  1. Yes, that’s fine. A Normal prior is mathematically equivalent to an L2-regularization. Given enough evidence from the data, it will overcome the limited range of your prior. (Alternatively you can increase the sd if you feel you don’t want as much regularization)

  2. pm.HalfNormal is positive only. You could try that.