jotaf98 / curveball
Second-order optimiser for deep networks
☆76Updated 5 years ago
Related projects: ⓘ
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 4 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆148Updated 7 years ago
- ☆81Updated 6 years ago
- TensorFlow implementation of (Momentum) Stochastic Variance-Adapted Gradient.☆45Updated 6 years ago
- Code for paper "Convergent Learning: Do different neural networks learn the same representations?"☆84Updated 8 years ago
- Learning Deep Parsimonious Representations, Deep Learning, Clustering, NIPS 2016☆14Updated 4 years ago
- Implementation of Coulomb GANs☆62Updated 3 years ago
- Lua implementation of Entropy-SGD☆79Updated 6 years ago
- Odds and Ends and Things I've implemented.☆78Updated 5 years ago
- Code for Attentive Recurrent Comparators☆57Updated 7 years ago
- A Tensorfflow implementation of Attend, Infer, Repeat☆82Updated 5 years ago
- Deep variational inference in tensorflow☆56Updated 6 years ago
- PyTorch implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks☆80Updated 6 years ago
- Structured Bayesian Pruning, NIPS 2017☆73Updated 4 years ago
- Forward-mode Automatic Differentiation for TensorFlow☆139Updated 6 years ago
- Tensorflow implementation of SGD with Coupled Adaptive Batch Size (CABS)☆43Updated 7 years ago
- ☆131Updated 6 years ago
- PixelVAE with or without regularization☆66Updated 7 years ago
- ☆64Updated 8 years ago
- TensorFlow-based implementation of "Attend, Infer, Repeat" paper (Eslami et al., 2016, arXiv:1603.08575).☆43Updated 6 years ago
- Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps☆40Updated 5 years ago
- Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)☆125Updated 6 years ago
- Code for "Deep Convolutional Networks as shallow Gaussian Processes"☆38Updated 5 years ago
- Weight initialization schemes for PyTorch nn.Modules☆70Updated 7 years ago
- Structured Receptive Fields in Convolutional Neural Networks☆47Updated 6 years ago
- Implementation of Real-NVP in Tensorflow☆102Updated 5 years ago
- ☆97Updated this week
- ☆219Updated 6 years ago
- Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"☆123Updated 5 years ago
- ☆63Updated this week