Evaluating variance in output

kyle-dorman / bayesian-neural-network-blogpost

Building a Bayesian deep learning classifier

https://medium.com/towards-data-science/building-a-bayesian-deep-learning-classifier-ece1845bc09

481 stars 105 forks source link

Evaluating variance in output #7

Open pengnam opened 5 years ago

pengnam commented 5 years ago

The model trains with both logits_variance and softmax as the output.

softmax is trained with the classification value

What is logits variance trained with?

pranavpandey2511 commented 4 years ago

@pengnam Its kind of a unsupervised learning. We use Monte carlo simulation to produce estimated true values for the variance of any given input and the prediction of NN is trained with those values.