Alternatives and similar repositories for ForwardForward

Users that are interested in ForwardForward are comparing it to the libraries listed below

• AllanYangZhou / universal_neural_functional
  ☆53Updated last year
• ago109 / predictive-forward-forward
  Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurren…
  ☆60Updated 2 years ago
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆61Updated last year
• orobix / fwdgrad
  Implementation of "Gradients without backpropagation" paper (https://arxiv.org/abs/2202.08587) using functorch
  ☆113Updated 2 years ago
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆87Updated 2 years ago
• louiskirsch / vsml-neurips2021
  Code for "Meta Learning Backpropagation And Improving It" @ NeurIPS 2021 https://arxiv.org/abs/2012.14905
  ☆33Updated 3 years ago
• TrentBrick / attention-approximates-sdm
  Code for the paper "Attention Approximates Sparse Distributed Memory"
  ☆25Updated 3 years ago
• machine-discovery / deer
  Parallelizing non-linear sequential models over the sequence length
  ☆54Updated 4 months ago
• google-deepmind / spectral_ssm
  ☆34Updated last year
• IDSIA / rtrl-elstm
  Official repository for the paper "Exploring the Promise and Limits of Real-Time Recurrent Learning" (ICLR 2024)
  ☆13Updated 4 months ago
• loeweX / Forward-Forward
  Reimplementation of Geoffrey Hinton's Forward-Forward Algorithm
  ☆157Updated last year
• TrentBrick / SDMContinualLearner
  ☆20Updated 2 years ago
• google-research / growneuron
  ☆56Updated last year
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆127Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆89Updated last year
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆40Updated 2 years ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆55Updated last year
• radarFudan / mamba-minimal-jax
  ☆34Updated 11 months ago
• microsoft / fnl_paper
  Factorized Neural Layers
  ☆30Updated 2 years ago
• johnryan465 / pscan
  ☆39Updated last year
• watcl-lab / positional_attention
  Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"
  ☆14Updated 5 months ago
• sustcsonglin / mamba-triton
  ☆48Updated last year
• oripress / EntropyEnigma
  Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"
  ☆53Updated last year
• AllanYangZhou / nfn
  NF-Layers for constructing neural functionals.
  ☆91Updated last year
• Cranial-XIX / longhorn
  Official PyTorch Implementation of the Longhorn Deep State Space Model
  ☆55Updated 11 months ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆68Updated last year
• KellerJordan / REPAIR
  Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
  ☆51Updated last year
• facebookresearch / MemoryMosaics
  Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
  ☆51Updated 9 months ago
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆99Updated last year
• schneiderkamplab / bitlinear
  BitLinear implementation
  ☆35Updated 10 months ago