btgraham / Batchwise-Dropout
Run fully connected artificial neural networks with dropout applied (mini)batchwise, rather than samplewise. Given two hidden layers each subject to 50% dropout, the corresponding matrix multiplications for forward- and back-propagation is 75% less work as the dropped out units are not calculated.
☆15Updated 9 years ago
Related projects: ⓘ
- On Certifying Non-uniform Bounds against Adversarial Attacks [ICML 2019]☆6Updated 5 years ago
- Slides for my graduate deep learning course at Imperial College.☆6Updated 5 years ago
- ☆14Updated 5 years ago
- A lightweight experimental logging library☆50Updated last month
- ☆5Updated 5 years ago
- A lightweight implementation of the SimCLR unsupervised training framework in PyTorch.☆7Updated 4 years ago
- A easy to use API to store outputs from forward/backward hooks in Pytorch☆36Updated 5 years ago
- Code for the CVPR 2020 [ORAL] paper "SAM: The Sensitivity of Attribution Methods to Hyperparameters"☆27Updated last year
- Semi-supervised learning via Compact Latent Space Clustering☆47Updated 5 years ago
- Exploring Random Encoders for Sentence Classification☆184Updated 4 years ago
- A library for evaluating representations.☆76Updated 2 years ago
- Web page for our tutorial on latent structure for NLP☆47Updated 5 years ago
- CE9010 Introduction to Data Analysis, 2020☆7Updated 4 years ago
- Materials for the practical sessions at EEML2019☆78Updated 4 years ago
- ☆6Updated last year
- Visualizing how deep networks make decisions☆66Updated 5 years ago
- There and Back Again: Revisiting Backpropagation Saliency Methods (CVPR 2020)☆52Updated 4 years ago
- ☆125Updated 6 years ago
- Collection of machine learning research paper references☆24Updated 2 months ago
- A PyTorch implementation of SSCR☆24Updated last month
- Deep learning model to identify a scene/character from 10 different animated movies☆29Updated 5 years ago
- ☆13Updated 4 years ago
- Implementation of Coulomb GANs☆62Updated 3 years ago
- ☆73Updated 4 years ago
- Original PyTorch implementation of the Leap meta-learner (https://arxiv.org/abs/1812.01054) along with code for running the Omniglot expe…☆148Updated last year
- Testing Nerual Tangent Kernel (NTK) on small UCI datasets☆82Updated 4 years ago
- Code repository for the paper "Attentive Group Equivariant Convolutional Neural Networks" published at ICML 2020. https://arxiv.org/abs/2…☆48Updated 4 years ago
- Forward-mode Automatic Differentiation for TensorFlow☆139Updated 6 years ago
- ☆62Updated 7 years ago
- Code in PyTorch for the convex combination linear IAF and the Householder Flow, J.M. Tomczak & M. Welling☆90Updated 7 years ago