That's a shame, I thought it was a quite interesting explanation of all those Google deep dream images.

There was another computerphile video just on the neural networks used, linked in the description, but I didn't watch it.

The most basic idea is reasonably straightforward - the neural networks are being used to classify images, so there is a low level categoriser for low level things like edges and corners, and then a higher level one that looks for how edges and corners are arranged to make, say, ears... and then a top level one to look for how ears and noses are arranged to make cats.

The complicated bit is that then they run the device backwards, so instead of using it to assign a probability that something is an ear, they actually put the ear in the image even though it wasn't really there to start with.

Since I'm not really saying anything that they didn't, I'm assuming that didn't help?

All I said is he had time to prepare, think over in his mind how he would present it (maybe there was even multiple takes)... gather himself. We could do the same for Sketch's trip.. and if there was anything in his story that moved him, perhaps he too would break into tears. I'm just saying you're weighing how he conducts himself as some sort of proof that what he described actually happened. Sketch'es trip seemed 100% real to him while he was in it (Salvia can cause you to forget what your actual surroundings are), just like going into a deep dream can do as well.

I see a video that was produced by, I assume, a church.. they even pulled in some actors, etc.. of course he's going to present things clearly and with poise.