muupan / deep-ensemble-uncertainty
An implementation of "Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles" (http://arxiv.org/abs/1612.01474)
☆34Updated 7 years ago
Related projects: ⓘ
- ☆69Updated 6 years ago
- Code for "Deep Convolutional Networks as shallow Gaussian Processes"☆38Updated 5 years ago
- Implementations of the ICML 2017 paper (with Yarin Gal)☆39Updated 6 years ago
- Repo for a paper about constructing priors on very deep models.☆69Updated 8 years ago
- Example implementation of the Bayesian neural network in "Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteri…☆31Updated 4 years ago
- ☆15Updated 7 years ago
- Python package to sample from determinantal point processes☆18Updated 9 years ago
- ☆15Updated this week
- Predictive State Recurrent Neural Networks☆18Updated 4 years ago
- Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors☆62Updated 4 years ago
- Gaussian Processes in Pytorch☆74Updated 4 years ago
- Demos demonstrating the difference between homoscedastic and heteroscedastic regression with dropout uncertainty.☆139Updated 8 years ago
- Code for doubly stochastic gradients☆25Updated 9 years ago
- Train a simple convnet on the MNIST dataset and evaluate the BALD acquisition function☆15Updated 7 years ago
- Implementation of Stochastic Gradient MCMC algorithms☆40Updated 7 years ago
- Multiplicative Normalizing Flow (MNF) posteriors for variational Bayesian neural networks☆64Updated 4 years ago
- Official implementation for the paper: "Shallow Updates for Deep Reinforcement Learning"☆18Updated 6 years ago
- Determinantal Point Processes in Python (NumPy)☆20Updated 7 years ago
- ☆17Updated this week
- Echo Noise Channel for Exact Mutual Information Calculation☆17Updated 4 years ago
- ☆25Updated 2 years ago
- Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019☆41Updated last year
- A clean TensorFlow implementation of Concrete Dropout☆23Updated 6 years ago
- ☆11Updated 8 years ago
- NeurIPS 2017 best paper. An interpretable linear-time kernel goodness-of-fit test.☆66Updated 5 years ago
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization☆37Updated 6 years ago
- Asymmetric Transfer Learning with Deep Gaussian Processes☆18Updated 9 years ago
- The Variational Homoencoder: Learning to learn high capacity generative models from few examples☆33Updated last year
- Code for the paper Implicit Weight Uncertainty in Neural Networks☆65Updated 4 years ago
- ☆39Updated 5 years ago