Part of the world of machine learning technologies and neural network, torch is an open source machine learning library, based Lua (using LuaJIT as scripting language).

Torch puts GPU first, and at its core, we find neural network and optimization libraries. It allows certain complex architectures to be built easily.

Lua is a more exotic language, but there is also a Python implementation of Torch: PyTorch.

Torch is a scientific computing framework with wide support for machine learning algorithms that puts GPUs first. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation.

At the heart of Torch are the popular neural network and optimization libraries which are simple to use, while having maximum flexibility in implementing complex neural network topologies. You can build arbitrary graphs of neural networks, and parallelize them over CPUs and GPUs in an efficient manner.

Torch is an open source  machine learning library, a scientific computing framework, and a script language based on the Lua programming language.[3] It provides a wide range of algorithms for deep machine learning, and uses the scripting language LuaJIT, and an underlying C implementation.