Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
- deep-learning
- deep-neural-networks
- gradient-descent
- automatic-differentiation
56,638 visible repositories in the index
337–360 of 458 · Most stars
Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
A .NET library that provides fast, accurate and automatic differentiation (computes derivative / gradient) of mathematical functions.
Syre workspace.
TranslatedAntifouling coating evidence panel: formulation sandbox, route biofouling stress, literature bounds. Simulation ≠ measurement. Live: https://simulator.jassyhong.top
Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo
PRnet is a flexible and scalable perturbation-conditioned generative model predicting transcriptional responses to unseen complex perturbations at bulk and single-cell levels.
A platform independent tensor library with autograd for the JVM
Toolbox for the analysis of smFISH images.
🔟 Implementation of rational number arithmetic for .NET with arbitrary precision.
An Elixir library for performing 2D and 3D mathematics.
The Configurable Math Library
slick is a simple to use polygon collision library inspired by bump.lua
Variations on Kirby & Paris' hydra battles and other entertaining math in Coq (collaborative, documented, includes exercises) [maintainer=@Casteran]
A library for placing labels in areas.
Fast detection of repackaged Android applications based on the comparison of resource files included into the package.
PyTorch implementation of the MIDAS algorithm for single-cell multimodal data integration (Nature Biotechnology 2024).
MAT is library for working with multi-dimensional arrays which supports efficient interfacing to foreign and CUDA code. BLAS and CUBLAS bindings are available.
Graph data structures with multiple heterogeneous metadata for Graphs.jl.
Peax is a tool for interactive visual pattern search and exploration in epigenomic data based on unsupervised representation learning with autoencoders
Research experiments exploring uncommon quant techniques.
An open-source mathematical tire modelling library
Machine learning for Analysis of Proteomics in Spatial biology - Nature Communications
Repository for paper scMulan: a multitask generative pre-trained language model for single-cell analysis.
The framework for quantification of neuronal anatomy