drasmuss / hessianfree
Hessian-free optimization for deep networks
☆60Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for hessianfree
- Weight initialization schemes for PyTorch nn.Modules☆70Updated 7 years ago
- Evaluation code with models for the paper "On the Quantitative Analysis of Decoder-Based Generative Models"☆130Updated 7 years ago
- Neural network training using iterated projections.☆89Updated 7 years ago
- Variational and semi-supervised neural network toppings for Lasagne☆208Updated 8 years ago
- ☆89Updated 8 years ago
- Lasagne code for weight normalization☆87Updated 8 years ago
- An implementation of the Hessian-free optimization algorithm in Theano☆61Updated 12 years ago
- An interface between Torch and Matlab☆31Updated 9 years ago
- ☆45Updated 8 years ago
- Efficient layer normalization GPU kernel for Tensorflow☆111Updated 7 years ago
- Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT☆204Updated 8 years ago
- This code accompanies the proximity variational inference paper.☆18Updated 5 years ago
- Complex number support for Torch☆43Updated 9 years ago
- Efficient implementation of Generative Stochastic Networks☆317Updated 8 years ago
- ☆76Updated 8 years ago
- Code for the recurrent image density estimator☆28Updated 9 years ago
- Experiment files for the paper "An Analysis of Unsupervised Pre-training in Light of Recent Advances", available here: http://arxiv.org/a…☆18Updated 8 years ago
- Topics on theoretical, mathematical aspects of DL☆71Updated 8 years ago
- Implementation of the VRAE☆59Updated 3 years ago
- ☆90Updated 7 years ago
- Code and models from the paper "Layer Normalization"☆245Updated 8 years ago
- Batch-Normalized LSTM (Recurrent Batch Normalization) implementation in Torch.☆92Updated 8 years ago
- Code for the "Binding via Reconstruction Clustering" paper☆21Updated 8 years ago
- Implementation of http://arxiv.org/abs/1511.05641 that lets one build a larger net starting from a smaller one.☆160Updated 8 years ago
- ☆38Updated 6 years ago
- MPI Parallel framework for training deep learning models built in Theano☆53Updated 7 years ago
- Working Theano implementation of Pixel RNN on MNIST.☆76Updated 8 years ago
- unitary matrix for hidden to hidden layer☆75Updated 7 years ago
- Code for paper "Full-Capacity Unitary Recurrent Neural Networks"☆55Updated 7 years ago