Good day! I implemented Bayesian neural network. All weights have normal distribution. I know that input data has different distributions for every feature ( normal, multinomial and soon). So my question is it a right idea to have conjunction distributions in the first layer.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Multi-dimensional input Bayesian Neural Network | 0 | 337 | February 20, 2024 | |
| Error in Defining Bayesian NN with Multivariate Gaussians | 1 | 220 | February 29, 2024 | |
| Bayesian Neural Network captures the mean response but not the variance in the training data | 11 | 1719 | August 10, 2021 | |
| Input Dimension mismatch error when modelling biases inside the HBNN tutorial | 4 | 1408 | February 27, 2019 | |
| Hierarchical Bayesian Neural Networks with Informative Priors by @twiecki | 6 | 2280 | July 15, 2021 |