# Not able to obtain Predicted values in Bayesian neural network

**URL:** <https://discourse.pymc.io/t/not-able-to-obtain-predicted-values-in-bayesian-neural-network/1889>\
**Category:** Questions\
**Created:** [September 10, 2018, 7:32am UTC](https://discourse.pymc.io/t/not-able-to-obtain-predicted-values-in-bayesian-neural-network/1889 "2018-09-10T07:32:24Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![simon\_o](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/simon_o/32/1619_2.png) [@simon\_o](https://discourse.pymc.io/u/simon_o)\
**Post date:** [September 24, 2018, 1:44pm UTC](https://discourse.pymc.io/t/not-able-to-obtain-predicted-values-in-bayesian-neural-network/1889/4 "2018-09-24T13:44:12Z")

</div>

There are many things that could be going wrong here, but maybe as a starting point you could have a look at the ADVI troubleshooting/tuning tips found in the thread:

> [@Poor Accuracy of ADVI for Linear Regression](https://discourse.pymc.io/t/poor-accuracy-of-advi-for-linear-regression/1077):
>
> I tried training a linear regression model using both ADVI and MCMC. ADVI is expected to have less accuracy than MCMC when both models are converged. However, I found that ADVI has unacceptable accuracy compare to the MCMC sampling. The script that was used for evaluation : import time import numpy as np import pymc3 as pm from sklearn.datasets import load\_diabetes, load\_boston from sklearn.metrics import mean\_squared\_error from sklearn.model\_selection import train\_test\_split from theano impo…

---

_[View the full topic](https://discourse.pymc.io/t/not-able-to-obtain-predicted-values-in-bayesian-neural-network/1889)._