Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)
-
Updated
Nov 3, 2016 - Python
#
fast-weights
Here are 10 public repositories matching this topic...
Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bootstrapping" (ICLR 2023 Workshop)
reinforcement-learning transformers pytorch fast-weights torchbeast fast-weight-programmers self-referential-weight-matrix rnn-based-few-shot-learning self-referential-learning
-
Updated
Dec 4, 2023 - Python
Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)
reinforcement-learning transformers language-modeling pytorch recurrent-neural-networks fast-weights torchbeast fast-weight-programmers
-
Updated
Mar 21, 2023 - Python
Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (NeurIPS 2022)
fast-weights neural-differential-equations neural-odes controlled-differential-equations fast-weight-programmers continuous-time-sequence-processing
-
Updated
Oct 21, 2022 - Python
PyTorch Language Modeling Toolkit for Fast Weight Programmers
-
Updated
Aug 24, 2023 - Python
Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023)
transformers generative-adversarial-network image-generation fast-weights fast-weight-programmers neural-learning-rules
-
Updated
Apr 25, 2023 - Python
Official repository for the paper "Automating Continual Learning"
cuda transformers pytorch fast-weights meta-learning continual-learning few-shot-learning fast-weight-programmers self-referential-weight-matrix self-referential-learning linear-transformers
-
Updated
Apr 1, 2024 - Python
PyTorch Implementation of the paper [Using Fast Weights to Attend to the Recent Past]
-
Updated
May 8, 2020 - Python
Official repository for the paper "Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions" (EMNLP 2023)
pytorch formal-languages fast-weights fast-weight-programmers self-referential-weight-matrix self-referential-learning linear-transformers
-
Updated
Oct 24, 2023 - Cuda
PyTorch implementation of DCT fast weight RNNs
-
Updated
May 7, 2021 - Python
Improve this page
Add a description, image, and links to the fast-weights topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the fast-weights topic, visit your repo's landing page and select "manage topics."