ducminhkhoi / autograd_pytorch
Building your own autograd mechanism based on PyTorch tensor only (not Variable, can be seen as numpy array)
☆18Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for autograd_pytorch
- A framework for implementing equivariant DL☆10Updated 3 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 3 years ago
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆47Updated last year
- STABILIZING GRADIENTS FOR DEEP NEURAL NETWORKS VIA EFFICIENT SVD PARAMETERIZATION☆16Updated 6 years ago
- NeurIPS 2019 Paper Implementation☆13Updated last year
- Minimum Description Length probing for neural network representations☆16Updated 2 weeks ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆60Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆30Updated 11 months ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆66Updated last year
- An adaptive training algorithm for residual network☆14Updated 4 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated last year
- A simple implementation of a deep linear Pytorch module☆18Updated 4 years ago
- ☆31Updated 10 months ago
- ☆49Updated 4 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- Python implementation of paper "AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks"☆14Updated 5 years ago
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- Factorized Neural Layers☆27Updated last year
- Automatically generate simple meta-learning tasks from a very large space☆15Updated last year
- JAX implementation of Graph Attention Networks☆13Updated 2 years ago
- Inference on non-linear dynamical systems written in JAX☆12Updated 4 years ago
- ☆22Updated 3 years ago
- solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning☆23Updated last year
- JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"☆43Updated 3 years ago
- Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defenses"☆13Updated 4 years ago
- Analogous Safe-state Exploration (ASE) is an algorithm for provably safe and optimal exploration in MDPs with unknown, stochastic dynamic…☆11Updated 3 years ago
- Tree Stack Memory Units☆17Updated 4 years ago
- Code for Neural Execution Engines: Learning to Execute Subroutines☆16Updated 3 years ago