greydanus / mnist1d
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.
☆217Updated 5 months ago
Alternatives and similar repositories for mnist1d:
Users that are interested in mnist1d are comparing it to the libraries listed below
- Compositional Linear Algebra☆466Updated this week
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆171Updated last week
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆371Updated this week
- Parameter-Free Optimizers for Pytorch☆122Updated 11 months ago
- Notebooks for the "JAX in Action" book☆135Updated 9 months ago
- Hierarchical Associative Memory User Experience☆100Updated last year
- A pure-functional implementation of a machine learning transformer model in Python/JAX☆177Updated last month
- The boundary of neural network trainability is fractal☆196Updated last year
- Hessian spectral density estimation in TF and Jax☆122Updated 4 years ago
- A functional training loops library for JAX☆86Updated last year
- Mathematical operations for JAX pytrees☆198Updated 3 months ago
- Oryx is a library for probabilistic programming and deep learning built on top of Jax.☆251Updated this week
- ☆99Updated 3 years ago
- ☆215Updated 8 months ago
- Neural Networks for JAX☆83Updated 6 months ago
- Materials of the Nordic Probabilistic AI School 2022.☆175Updated 2 years ago
- A Pytree Module system for Deep Learning in JAX☆213Updated 2 years ago
- ☆423Updated 5 months ago
- Automatic gradient descent☆207Updated last year
- Uncertainty quantification with PyTorch☆349Updated last week
- A framework for conducting machine learning experiments in python☆38Updated 3 months ago
- A Python package of computer vision models for the Equinox ecosystem.☆103Updated 8 months ago
- ☆60Updated 3 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆185Updated 3 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆222Updated 3 weeks ago
- An alternative to convolution in neural networks☆254Updated last year
- 🧱 Modula software package☆176Updated last week
- Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).☆108Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- NumPy arrays, ready for human consumption☆68Updated 8 months ago