Facebook launches open source Torchnet toolkit to enable new AI experiments

Intending to take artificial intelligence (AI) to new levels, Facebook has launched Torchnet. The open source software toolkit is based on the deep machine learning framework Torch, and will foster rapid and collaborative development of deep learning developments by the Torch community.

Debuted at the International Conference on Machine Learning (ICML) in New York, Torchnet uses AI concepts through a series of boilerplate code, key abstractions and reference implementations. The offerings through the toolkit can be combined or reused separately to drive further developments among researchers in the field of deep machine learning.

“We created Torchnet to give researchers clear guidelines on how to set up their code, and boilerplate code that helps them develop more quickly. The modular Torchnet design makes it easy to test a series of coding variants focused around the data set, the data loading process, and the model, as well as optimisation and performance measures,” the Torchnet team members, led by Facebook’s Artificial Research (FAIR) lab, wrote in a blog post.

Torchnet is written in the multi-paradigm programming language, Lua. It is designed to run on any device with a standard x86 chip.

Facebook is not the only tech company that has started viewing deep learning with keen interest. Starting from Amazon and Google to Microsoft, all the leading players are in the race to expand their presence in the world of AI with their offerings. In fact, Twitter is already using the same Torch framework to build machine learning software.