I was trying to use one hidden layer neural network model to predict the observing data rainfall (target value, the red dots), which shouldn’t be negative. This result of each day contains 1000 predictions, which was calculated as probability density and shown with the different shades of blue (It’s…

Limit or prevent unrealistic output of neural network

junpenglao February 19, 2018, 8:34pm 2

You can try modeling the observed using a distribution defined in (0, inf). For example, HalfNormal, logNormal.

Topic		Replies	Views
Positive samples Questions theano	1	450	August 4, 2018
Bad initial energy: inf or nan Questions	1	1528	March 30, 2018
Bayesian NN classifier predicts data from 0 to 0.5 and not 0 to 1 Questions gpu , theano	6	937	November 22, 2017
Define constraint on the priors Questions	12	2147	April 19, 2018
Negative Binomial Distribution with logp = -inf Questions	14	1567	July 11, 2018