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
47,133 repositories indexed
265–288 of 372 · 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
means completeness and balancing, from the Arabic word الجبر
A .NET library that provides fast, accurate and automatic differentiation (computes derivative / gradient) of mathematical functions.
Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo
Rails frontend to The Genome Institute's drug gene interaction database.
PRnet is a flexible and scalable perturbation-conditioned generative model predicting transcriptional responses to unseen complex perturbations at bulk and single-cell levels.
🔟 Implementation of rational number arithmetic for .NET with arbitrary precision.
A GDScript port of Delaunator: A fast library for Delaunay triangulation of 2D points.
TypeDB Bio: Biomedical Knowledge Graph
The Mines Java Toolkit
BulkFormer: A large-scale foundation model for human bulk transcriptomes
The Massively Parallel Quantum Chemistry program, MPQC, computes properties of atoms and molecules from first principles using the time independent Schrödinger equation.
Variations on Kirby & Paris' hydra battles and other entertaining math in Coq (collaborative, documented, includes exercises) [maintainer=@Casteran]
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions
NeuroAnatomy Toolbox: An R package for the (3D) visualisation and analysis of biological image data, especially tracings of single neurons.
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.
An ActionScript 3 Geometry Library
Python package for analysis of multiomic single cell RNA-seq and ATAC-seq.
Peax is a tool for interactive visual pattern search and exploration in epigenomic data based on unsupervised representation learning with autoencoders
A matrix package for common lisp building on work by Mark Hoemmen, Evan Monroig, Tamas Papp and Rif.
Research experiments exploring uncommon quant techniques.
A command line weather app built using elixir