fast-weight-programmers

There are 9 repositories under fast-weight-programmers topic.

  • IDSIA/modern-srwm

    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)

    Language:Python1737217

  • IDSIA/recurrent-fwp

    Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)

    Language:Python50905

  • kazuki-irie/kv-memory-brain

    Official Code Repository for the paper "Key-value memory in the brain"

    Language:Jupyter Notebook28402

  • IDSIA/neuraldiffeq-fwp

    Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (NeurIPS 2022)

    Language:Python23404

  • IDSIA/lmtool-fwp

    PyTorch Language Modeling Toolkit for Fast Weight Programmers

    Language:Python18514

  • IDSIA/automated-cl

    Official repository for the paper "Automating Continual Learning"

    Language:Python16503

  • IDSIA/fpainter

    Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023)

    Language:Python12403

  • IDSIA/fwp-formal-lang

    Official repository for the paper "Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions" (EMNLP 2023)

    Language:Cuda5401

  • kazuki-irie/dct-fast-weights

    PyTorch implementation of DCT fast weight RNNs

    Language:Python5100