samiraabnar / Reflect
Official Implementation of "Transferring Inductive Biases Through Knowledge Distillation"
☆14Updated 4 years ago
Alternatives and similar repositories for Reflect:
Users that are interested in Reflect are comparing it to the libraries listed below
- ☆24Updated 3 years ago
- Implementation of the GLOM model for text☆11Updated 4 years ago
- ☆11Updated 3 years ago
- Usable implementation of Mogrifier, a circuit for enhancing LSTMs and potentially other networks, from Deepmind☆17Updated 9 months ago
- ☆24Updated 10 months ago
- hierarchical convolutional attention networks for text classification☆16Updated 5 years ago
- A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transfor…☆47Updated last year
- Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthog…☆17Updated 5 years ago
- Layerwise Relevance Visualization in Convolutional Text Graph Classifiers☆12Updated 3 years ago
- ☆34Updated 6 years ago
- Repository of state of the art text/documentation classification algorithms in Pytorch.☆10Updated 6 years ago
- Code for gradient rollback, which explains predictions of neural matrix factorization models, as for example used for knowledge base comp…☆21Updated 4 years ago
- Open source implementation of SeaRNN (ICLR 2018, https://openreview.net/forum?id=HkUR_y-RZ)☆48Updated 6 years ago
- ☆14Updated 5 years ago
- Tensorflow port implementation of Single Headed Attention RNN☆16Updated 5 years ago
- Pretrained TorchVision models on CIFAR10 dataset (with weights)☆24Updated 4 years ago
- MTAdam: Automatic Balancing of Multiple Training Loss Terms☆36Updated 4 years ago
- (ICML 2021) Mandoline: Model Evaluation under Distribution Shift☆31Updated 3 years ago
- Code for our paper: "Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers".☆21Updated 3 years ago
- The Shape of Data: Intrinsic Distance for Comparing Data Distributions☆12Updated 5 years ago
- Source code repo for paper "TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation"☆10Updated last year
- ☆19Updated 5 years ago
- ☆24Updated 5 years ago
- SNAIL Attention Block for Keras.☆16Updated 4 years ago
- ☆17Updated 5 years ago
- Code publication to the paper "Normalized Attention Without Probability Cage"☆16Updated 3 years ago
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Updated 3 years ago
- PhD thesis (updating) of Jiatao Gu from HKU☆19Updated 6 years ago
- codes for TokenManipulationGAN☆7Updated 4 years ago
- Code repo for "Transformer on a Diet" paper☆31Updated 4 years ago