Torch is a scientific computing framework with broad support for machine learning algorithms that put GMOs first. Easy and fast scripting language is easy and efficient to use thanks to LuaJIT and an underlying C/CUDA application.
- A powerful N-size array
- indexing, slicing, transfer support
- Incredible interface support for C via LuaJIT
- Linear algebra routines
- Neural network and energy-based models
- Numerical optimization routines
- Fast and efficient GPU support
- Can be buried with iOS and Android backend ports
Why Use torch?
Torch's goal is to achieve maximum flexibility and speed in creating your scientific algorithms while making the process extremely simple. Torch comes with a wide ecosystem of community-guided packages in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking, and is built on the Lua community.
At the heart of Torch is the popular neural network and optimization libraries that are easy to use, while complex neural network topologies have maximum flexibility in practice. You can create arbitrary graphics of neural networks and efficiently parallel them to CPUs and GPUs.
Use of Torch
Torch is constantly evolving: it is already being used in Facebook, Google, Twitter, NYU, IDIAP, Purdue and many other companies and research laboratories.