Novigrad is an automatic differentiation engine with a forward mode and a backward mode. It aims to be a minimalistic neural network framework written in Rust. It's a work-in-progress.
-
Updated
Apr 28, 2024 - Rust
Novigrad is an automatic differentiation engine with a forward mode and a backward mode. It aims to be a minimalistic neural network framework written in Rust. It's a work-in-progress.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
⟨Grassmann-Clifford-Hodge⟩ multilinear differential geometric algebra
On-device AI across mobile, embedded and edge for PyTorch
A Machine Learning framework from scratch in Pure Mojo 🔥
Economic analysis tool using tensor PCA modeling to interpolate GNP values, integrating tensor product, PCA, and linear regression for better interpolation.
Biblioteca para manipulação de modelos de Redes Neurais
Code for Crystallographic Vorticity Axis analysis [applied principal geodesic analysis, PGA]
C++ DataFrame for statistical, Financial, and ML analysis -- in modern C++ using native types and contiguous memory storage
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
Tensor-based Multiple Canonical Correlation Analysis
Pytorch_Dart is a dart wrapper for Libtorch,striving to provide an experience identical to PyTorch. You can use it as an alternative to Numpy in your Dart/Flutter projects.
Estimation of elastic waves velocities in anisotropic solids
Parabolic PDE resolution with Tensor Networks using Backward-Forward Stochastic Differential Equations
Add a description, image, and links to the tensor topic page so that developers can more easily learn about it.
To associate your repository with the tensor topic, visit your repo's landing page and select "manage topics."