Comments (3)
Thanks for your question,
I believe there are no convolutional layers in this repoβs code. I imagine you are referring to variational dropout, as presented in https://papers.nips.cc/paper/5666-variational-dropout-and-the-local-reparameterization-trick.pdf, where activations are multiplied with Gaussian noise. This scenario, can be seen as placing a variational distribution over the weights q(w_{i})=N(w_{i}; \mu_{i}, \alpha\mu_{i}^{2}) where \alpha is shared among all weights. The authors choose to use an improper prior over the weights and compute KL(q(W) || p(W)) using an expansion approximation. If you were to place a Gaussian prior over the weights p(W) = N(W; 0, I), you would calculate the KL term as: KL(N(w_{i}; \mu_{i}, \alpha\mu_{i}^{2}) || p(W)). This expression has a closed-form solution. However, it is unclear to me if this prior is a sensible choice when applying multiplicative Gaussian noise.
In our implementation, we place a factorised Gaussian approximate distribution over weights q(w_{i})=N(w_{i}; \mu_{i},\sigma_{i}^{2}). A Gaussian prior is used. The local reparametrization trick can be applied to these distributions, inducing Gaussians over activations q(a_{j} | x)=N(β¦). This reduces the variance in the gradient estimator for the likelihood of the data. The KL divergence, however, is still calculated in weight space KL(q(W) || p(W)). This expression can be evaluated in closed form.
from bayesian-neural-networks.
Hi again @ShellingFord221,
I have seen that you have opened multiple issues with theoretical questions. Although the feedback is appreciated, these sections are best left for issues with the actual code. I would refer you to the original work: https://arxiv.org/abs/1505.05424 for a better theoretical understanding of the implemented approaches.
from bayesian-neural-networks.
I'm really sorry that I just want to have some discussions about both implementation and theory of BBB...
from bayesian-neural-networks.
Related Issues (20)
- bbp_hetero uncertainties plot HOT 2
- Energy Efficient dataset HOT 1
- Posterior Predictive Distribution HOT 5
- [Question] BBB vs BBB w/ Local Reparameterization HOT 4
- About calculating the logarithm of the Gaussian mixture model HOT 1
- UCI log likelihood calculation HOT 5
- Scaling langevin noise HOT 2
- Looking for the implementation of "Getting a GlUE" HOT 1
- Thank you!
- [Question][MC dropout] drop hidden units for each data point or for each mini-batch data? HOT 1
- code implementation HOT 1
- May I ask the code about calculating the Hessian in the Kronecker-Factorised Laplace methods? HOT 1
- Question: log_gaussian_loss function used in MC Dropout and SGLD HOT 1
- this code is writen in python 2.7 .can this code change to the envriment of python 3.6 HOT 1
- 2 questions: batch & layer HOT 1
- a question about the calculation of uncertainty HOT 1
- about sample or not when training HOT 1
- bbp_hetero notebook is not using three layers HOT 1
- Panda not reading the first row HOT 1
- BNN Bayesian Online Learning HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bayesian-neural-networks.