greydanus / mnist1dLinks
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.
☆234Updated last year
Alternatives and similar repositories for mnist1d
Users that are interested in mnist1d are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆188Updated this week
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- Uncertainty quantification with PyTorch☆377Updated 2 months ago
- A pure-functional implementation of a machine learning transformer model in Python/JAX☆181Updated 7 months ago
- Compositional Linear Algebra☆503Updated 4 months ago
- A general-purpose, deep learning-first library for constrained optimization in PyTorch☆147Updated last month
- ☆161Updated 2 years ago
- ☆100Updated 4 years ago
- A Python package of computer vision models for the Equinox ecosystem.☆109Updated last year
- A functional training loops library for JAX☆88Updated last year
- Hierarchical Associative Memory User Experience☆105Updated last month
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆404Updated last week
- Named tensors with first-class dimensions for PyTorch☆332Updated 2 years ago
- A Pytree Module system for Deep Learning in JAX☆214Updated 2 years ago
- Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes…☆248Updated 5 years ago
- Loopy belief propagation for factor graphs on discrete variables in JAX☆163Updated last year
- The boundary of neural network trainability is fractal☆221Updated last year
- ☆460Updated last year
- JAX Arrays for human consumption☆110Updated last month
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions☆259Updated 2 years ago
- 🧱 Modula software package☆316Updated 4 months ago
- ☆60Updated 3 years ago
- Oryx is a library for probabilistic programming and deep learning built on top of Jax.☆288Updated last week
- Named Tensors for Legible Deep Learning in JAX☆215Updated last month
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆191Updated last year
- A framework for conducting machine learning experiments in python☆43Updated last year
- Hessian spectral density estimation in TF and Jax☆124Updated 5 years ago
- ☆251Updated last week
- Mathematical operations for JAX pytrees☆205Updated last year
- Neural Networks for JAX☆84Updated last year