tu-rbo / concarne
Lightweight framework for learning with side information (aka privileged information), based on Theano and Lasagne. For more info on learning with side information see http://arxiv.org/abs/1511.06429
☆17Updated 8 years ago
Related projects ⓘ
Alternatives and complementary repositories for concarne
- Code and data accompaning the paper "Learning State Representations with Robotic Priors" (Jonschkowski and Brock, 2015).☆18Updated 7 years ago
- Fastidious accounting of entropy streams into and out of optimization and sampling algorithms.☆31Updated 8 years ago
- Python package for inference with Gaussian processes☆11Updated 9 years ago
- Learning algorithms introduced in "A PAC-Bayes Sample Compression Approach to Kernel Methods" (ICML 2011)☆9Updated 10 years ago
- Hidden Markov Models (HMMs) with tied states and autoregressive observations☆23Updated 4 years ago
- This code accompanies the proximity variational inference paper.☆18Updated 5 years ago
- ☆11Updated 3 years ago
- A Newton ADMM based solver for Cone programming.☆38Updated 7 years ago
- Look Ahead Hamiltonian Monte Carlo☆30Updated 9 years ago
- Fun with variational autoencoders.☆11Updated 6 years ago
- Implementation of Variance Reduction Techniques in Julia☆11Updated 8 years ago
- Visualizes gradient descent techniques on functions of two variables f(x, y): Stochastic Gradient Descent, Momentum, Nesterov's Accelerat…☆13Updated 7 years ago
- Stochastic Gradient MCMC algorithms implemented in theano (and autograd)☆9Updated 7 years ago
- Sticky hierarchical Dirichlet process hidden Markov model for time series denoising☆44Updated 8 years ago
- Neural model of hierarchical reinforcement learning☆16Updated 7 years ago
- Experiments from the article "Tensorial Mixture Models"☆25Updated 6 years ago
- C++ code for the RDIS algorithm from "Recursive Decomposition for Nonconvex Optimization." Friesen and Domingos, IJCAI 2015.☆57Updated 9 years ago
- Variational Walkback, NIPS'17☆28Updated 7 years ago
- An iterative neural autoregressive distribution estimator (NADE-K)☆26Updated 10 years ago
- BBRL is a C++ open-source library used to compare Bayesian reinforcement learning algorithms☆33Updated 8 years ago
- This repository houses the code for the community website http://www.probabilistic-numerics.org☆35Updated 4 years ago
- AA120Q Course Materials☆28Updated last month
- A Python library for reinforcement learning using Bayesian approaches☆53Updated 9 years ago
- Rectified Factor Networks☆38Updated 5 years ago
- Backpropagate derivatives through the Cholesky decomposition☆58Updated 4 years ago
- Disciplined convex stochastic programming. For the cvxstoc home page, please see:☆31Updated 4 years ago
- Implementation of Trimmed Grassmann Average (TGA) by Hauberg S et al. in Python☆23Updated 9 years ago
- Reducing Reparameterization Gradient Variance code.☆33Updated 7 years ago