A visual programming language for networks of neural networks
Marcelo Coelho
Diego Pinochet
NNN is a dataflow and visual programming environment that leverages the power of artificial intelligence for creative applications.  Recent advances in deep learning anticipate a future where design and creativity will be automated by new forms of machine intelligence, empowering humans with extraordinary abilities. However, these new tools are limited, difficult to learn and use, and have remained inaccessible to most people.

Using a node-based graphical user interface, NNN abstracts away some of the complexities of machine learning and allows users to train and create ‘networks of neural networks’, scaffolding simpler models into increasingly complex behaviors and interactions. While neural networks are not inherently able to discover, store, and apply skills across a variety of problems and domains, humans are capable of quickly learning and creating new representations by combining existing primitive elements.  By creating interfaces that leverage what humans and machines do best, we can create more powerful, generalizable and accessible tools.

NNN is built with p5.js, Litegraph and Electron.