I also wonder whether this is computationally feasible. If you literally had to search through all possible brains until you found the right one, then you would never get anywhere (for even a single person, let alone history). But it’s not clear whether any more efficient algorithm exists: inferring the neural net weights from a recorded input-output trace seems like it could be a hard problem.
“Right one” is a relative concept. I would like to recreate my grandfather, but my knowledge of him would probably only fill a page of text or so. Thus it is much much easier to recreate a being that passes my personal grandfather turing test than it would be to create a being that satisfies my internal model of my father (of whom I know much more).
The recreations only have to be accurate to the point of complete consistency with surviving evidence.
On the neural net issue, the exact weights certainly don’t matter so much. There’s massive redundancy at multiple levels. Every one has V1 layers which are specifically unique, but they all functionally do almost exactly the same thing.
I also wonder whether this is computationally feasible. If you literally had to search through all possible brains until you found the right one, then you would never get anywhere (for even a single person, let alone history). But it’s not clear whether any more efficient algorithm exists: inferring the neural net weights from a recorded input-output trace seems like it could be a hard problem.
“Right one” is a relative concept. I would like to recreate my grandfather, but my knowledge of him would probably only fill a page of text or so. Thus it is much much easier to recreate a being that passes my personal grandfather turing test than it would be to create a being that satisfies my internal model of my father (of whom I know much more).
The recreations only have to be accurate to the point of complete consistency with surviving evidence.
On the neural net issue, the exact weights certainly don’t matter so much. There’s massive redundancy at multiple levels. Every one has V1 layers which are specifically unique, but they all functionally do almost exactly the same thing.