teuthid Goto Github PK

Teuthid is a free open source framework, which implements multilayer artificial neural networks in C++ with support for both fully connected and sparsely connected networks. Cross-platform execution in floating-point numbers are supported with more range and precision than C++'s ordinary built-in types. The framework is designed to support multi-core CPU/GPGPU computing platforms based on OpenCL.

• Multilayer artificial neural network libraries in C++14.
• Multiple-precision floating-point computation (requires MPFR and GMP libraries).
• Thread-safe components with support for C++14 thread-local storage.
• Versatile (possible to adjust many parameters and features).
• Use OpenCL (optionally) as its interface for executing code on parallel devices such as GPUs and multi-core CPUs.
• Rigorously tested using Boost.Test library.
• Open source, but can be used in commercial applications (licenced under GNU LGPL v3).
• ...

Refer to README file for more details.