A wrapper around tensor2tensor to felxibly train, interact, and generate data for neural chatbots. Please also check the wiki page for my notes on over 150 papers.
An online chatbot using a state-of-the-art neural network (GPT2) trained on 5 different languages and various datasets.
An open-source pipeline for building dialogue datasets in many languages using books from Project Gutenberg.
Easily simulate the change of dipole moments of complex protein structures and provide a 3D UI in OpenGL. There are also several searching algorithms implemented to find protein structures that satisfy user defined logic functions. Download here.
Brainstream: machine learning driven BCI that translates thoughts into text