jelennal / t1t2Links
Theano implementation of T1-T2 gradient-based method for tuning continuous hyperparameters.
☆10Updated 9 years ago
Alternatives and similar repositories for t1t2
Users that are interested in t1t2 are comparing it to the libraries listed below
Sorting:
- Trained network models for Torch☆10Updated 10 years ago
- For training very deep networks☆10Updated 8 years ago
- Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT☆208Updated 10 years ago
- Variational and semi-supervised neural network toppings for Lasagne☆210Updated 9 years ago
- ☆89Updated 9 years ago
- A theano implementation of Hinton's dropout.☆144Updated 11 years ago
- Exploring differentiation with respect to hyperparameters☆296Updated 10 years ago
- Stochastic gradient routines for Theano☆103Updated 7 years ago
- Collection of useful, re-used routines.☆45Updated 8 years ago
- A Neural Turing Machine implementation in Torch.☆278Updated 10 years ago
- Deep generative models for semi-supervised learning.☆109Updated 9 years ago
- An implementation of the RL-NTM from http://arxiv.org/abs/1505.00521☆160Updated 10 years ago
- supercell☆192Updated 8 years ago
- Implementation of http://arxiv.org/abs/1511.05641 that lets one build a larger net starting from a smaller one.☆159Updated 9 years ago
- A set of distributed learning algorithms for Torch☆93Updated 4 years ago
- Benchmarks for several RNN variations with different deep-learning frameworks☆171Updated 6 years ago
- Exercises for the semi-supervised summer school https://semisupervised-learning.compute.dtu.dk.☆11Updated 9 years ago
- Reading Group on Reinforcement Learning topics☆56Updated 9 years ago
- Hierarchical Softmax Layer☆18Updated 10 years ago
- Non-parametric Bayesian in Python, including Indian buffet process (IBP), hierarchical Dirichlet process (HDP).☆73Updated 10 years ago
- This is a self contained software accompanying the paper titled: Learning Longer Memory in Recurrent Neural Networks: http://arxiv.org/ab…☆168Updated 8 years ago
- A rudimentary wrapper around the fast Maxwell kernels for GEMM and convolution operations provided by nervanagpu☆34Updated 10 years ago
- Hyperparameter optimization with approximate gradient☆66Updated 4 years ago
- Topics on theoretical, mathematical aspects of DL☆72Updated 9 years ago
- ☆64Updated 8 years ago
- ☆60Updated 10 years ago
- An implementation of the Hessian-free optimization algorithm in Theano☆61Updated 14 years ago
- unitary matrix for hidden to hidden layer☆76Updated 8 years ago
- Code for reproducing the results on the MNIST dataset in the paper "Distributional Smoothing with Virtual Adversarial Training"☆110Updated 8 years ago
- Implementation of the VRAE☆60Updated 4 years ago