Comments (1)
Hi @Aadesh-1404 ,
This is actually a difference in the models - the DGP model used in PyDeepGP is from Damianou and Lawrence (2013) and uses latent variables in the intermediate layers, whereas the model we follow is from Salimbeni and Deisenroth (2017), and doesn't use latent variables. This means that the fits will be different. However, you should be able to get similar fits (but not exactly the same) using GPflux by following the tutorial https://secondmind-labs.github.io/GPflux/notebooks/deep_cde.html
References
Damianou and Lawrence (2013): http://proceedings.mlr.press/v31/damianou13a
Salimbeni and Deisenroth (2017): https://arxiv.org/abs/1705.08933
from gpflux.
Related Issues (20)
- Clean up BayesianDenseLayer
- Attempting to learn models with multidimensional inputs leads to an error. HOT 6
- Optimisation problem in gpflux HOT 1
- Enquiry about model.predict() with batch_size and sampling from each layer after model fitting
- Usage of NatGradModel/Wrapper to train variational parameters
- GPLayer doesn't seem to support multiple input units HOT 3
- GPLayer's prediction seems to be too confident HOT 3
- Customize NatGrad Model to turn off variational parameters in hidden layers HOT 3
- ModelCheckpoint with save_weights_only=False crashes HOT 3
- GPflux for text classification? HOT 2
- Bug when computing the mean of marginal variational q(f) HOT 3
- Relax tensorflow versions
- Incorrect WilsonSample for multioutput case
- How to save a DeepGP model
- dtype errors on using the model if keras backend is not set to float64
- Add version upper bound before adjust gpflow>=2.6 HOT 4
- Fix for new GPflow heteroskedastic likelihood breaks for quadrature dependent likelihoods
- DistributionLambda for latent variable amortization/recognition networks/encoders
- Protobuf minor version pin HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gpflux.