<div dir="auto"><a href="https://siliconangle.com/blog/2017/05/28/startup-uses-ai-create-gui-source-code-simple-screenshots/" target="_blank">https://siliconangle.com/blog/<wbr>2017/05/28/startup-uses-ai-<wbr>create-gui-source-code-simple-<wbr>screenshots/</a><div dir="auto"><br></div><div dir="auto"><a href="https://research.googleblog.com/2017/06/multimodel-multi-task-machine-learning.html?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed:+blogspot/gJZg+(Official+Google+Research+Blog)&utm_content=Netvibes&m=1">https://research.googleblog.com/2017/06/multimodel-multi-task-machine-learning.html?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed:+blogspot/gJZg+(Official+Google+Research+Blog)&utm_content=Netvibes&m=1</a><br></div><div dir="auto"><br></div><div dir="auto">Anyone want to embark on a "Machine Learning of X3D JSON" paper with me, or even VRML?   I am thinking of a model which will generate JSON from a rendering and an LSTM, like the first paper.</div></div>