Machine learning is used to generating videos from photos

Researchers from MIT attempting to solve this problem have come up with some very impressive results, using specially trained neural networks to turn images into videos and getting the computer to essentially predict what happens next. Currently their model has plenty of limitations but it’s still an impressive feat of machine imagination, and another step toward computers that understand the world a little more like humans.

The neural net was trained using more than 2 million videos downloaded from Flickr.Using this data, the team’s neural nets were able to not only generate short videos that resembled these scenes but to also look at a still and create footage that might follow  This essentially predicting what will happen next, albeit in a limited manner that is only guessing how pixels might change, rather than understanding the scene.

How long till we can run it on live security cams to generate predictive analysis of the near future.There's nothing stopping us from doing that right now. Of course it's predictive analysis will have absolutely no correlation to the actual future reality and never will, which makes it completely useless; but there's no reason a neural network can't guess at the future just like you can.