We have collection of more than 1 Million open source products ranging from Enterprise product to
small libraries in all platforms. We aggregate information from all open source repositories.
Search and find the best for your needs. Check out projects section.
Gosl is a Go library to develop Artificial Intelligence and High-Performance Scientific Computations. The library tries to be as general and easy as possible. Gosl considers the use of both Go concurrency routines and parallel computing using the message passing interface (MPI). Gosl has several modules (sub-packages) for a variety of tasks in scientific computing, image analysis, and data post-processing.
Distributed Deep Learning with Apache Spark and Keras. Distributed Keras is a distributed deep learning framework built op top of Apache Spark and Keras, with a focus on "state-of-the-art" distributed optimization algorithms. We designed the framework in such a way that a new distributed optimizer could be implemented with ease, thus enabling a person to focus on research. Several distributed methods are supported, such as, but not restricted to, the training of ensembles and models using data parallel methods.
The library contains a number of interconnected Java packages that implement machine learning and artificial intelligence algorithms. These are artificial intelligence algorithms implemented for the kind of people that like to implement algorithms themselves. See Issues page.
The code has been tested on OSX and Linux. The C-OPT library contains a pure Python implementation (using Numba) of the sequential algorithm. Note that because Numba lacks atomic types, a pure Python implementation of the parallel algorithm is not straightforward.
pagmo (C++) or pygmo (Python) is a scientific library for massively parallel optimization. It is built around the idea of providing a unified interface to optimization algorithms and to optimization problems and to make their deployment in massively parallel environments easy. If you are using pagmo/pygmo as part of your research, teaching, or other activities, we would be grateful if you could star the repository and/or cite our work. The DOI of the latest version and other citation resources are available at this link.
The GDLibrary is a pure-Matlab library of a collection of unconstrained optimization algorithms. This solves an unconstrained minimization problem of the form, min f(x). Note that the SGDLibrary internally contains this GDLibrary.
The SGDLibrary is a pure-MATLAB library of a collection of stochastic optimization algorithms. This solves an unconstrained minimization problem of the form, min f(x) = sum_i f_i(x). The SGDLibrary is also operable on GNU Octave (Free software compatible with many MATLAB scripts). Note that this SGDLibrary internally contains the GDLibrary.
StructuredOptimization.jl is a high-level modeling language that utilizes a syntax that is very close to the mathematical formulation of an optimization problem. StructuredOptimization.jl can handle large-scale convex and nonconvex problems with nonsmooth cost functions.
ForBES (standing for Forward-Backward Envelope Solver) is a MATLAB solver for nonsmooth optimization problems. It is generic in the sense that the user can customize the problem to solve in an easy and flexible way. It is efficient since it features very efficient algorithms, suited for large scale applications.
This project generates animations of pytorch optimizers solving toy problems. Examples Below. Some nice animations were posted a few years ago by Alex Radford but didn't include the Adam optimizer or landscapes with noise. Louis Tiao blogged about how to make the visualizations. The pytorch unit tests show how to run the optimizers on test functions. I pulled these together and shared the result at https://github.com/wassname/viz_torch_optim.
CIlib is a library of various computational intelligence algorithms. The goal of the project is to create a library that can be used and referenced by individuals and researchers alike. CIlib is not a "framework", instead the library is a set of a few very simple abstractions, and allows for a principled manner to define computational intelligence algorithms and uses several typeclasses such as Functor and Monad.
Package for large scale convex optimization solvers in julia. This package is intended to allow for easy implementation, testing, and running of solvers through the Convex.jl interface. The package is currently under active development and uses the ProximalOperators.jl package to do the low level projections. These values correspond to the values in the paper Conic Optimization via Operator Splitting and Homogeneous Self-Dual Embedding (O'Donoghue et.al).