> Reportedly, von Neumann possessed an eidetic memory, and so was able to recall complete novels and pages of the phone directory on command. This enabled him to accumulate an almost encyclopedic knowledge of what ever he read
If he was able to recall ~entire pages of the phone directory on command, I wonder if he could also recall (near) verbatim text of all the novels he had ever read, to what degree he could do this, or to what degree he could at least comprehensively recall key points, facts, timelines.
I would think he would have spent some time speculating on how the brain stores memories, I wonder if any of his theories were ever captured in some form.
Supposedly, yes-- during his final stay in the hospital, his brother read to him from a book they'd enjoyed during their childhood, Dickens' A Tale of Two Cities.
When his brother had to turn the page, John would continue the narration from memory while his brother found his place on the subsequent page.
Given that he could be occasionally absent minded, I suspect that it had to be something that piqued his interest, but his sense of what was interesting was extremely broad.
He did in fact speculate on the workings of the brain in The Computer and the Brain, which is based on a lecture series he had planned out but did not deliver.
It was more in the context of automata theory, but as someone with an interest in AI, automata, and neuroscience, it was frankly rather dank[0].
A lot of the pioneering work was, and is enjoyable in part because it's original and speculative, so you don't have to master the literature to make sense of it, you can just pick a paper and go. I'd recommend reading Pitts and McCullogh, plus also Lettvin, but others might have some equally lit[1] recommendations.
--
0. In the contemporary sense, c.f. "cool", "dope", or "excellent"; not dank like a root cellar.
My word choice is more driven by exposure to the dataset that I'm working with.
There's been some recent successes with autoencoders trained on virtual sensory input (i.e., video games) with surprising results, e.g., neural networks that can simulate the dynamics of these environments with surprising fidelity.
Of course, learning to play video games at a high level is trivially easy, as everyone in the field now knows.
The next challenge is, naturally, to make money doing this.
But how?
After the traditional thirty seconds of research before undertaking a major project, I determined that the only way to make money from video games is to become a popular streamer.
So now I am training an agent to generate video of it playing and reacting to an imaginary game and equally fictitious Twitch viewers, with a dataset drawn from the top Fortnite streamers.
The reward function is comprised of a blend of subscribers, donations, and (logarithmically scaled) misogyny in the chat.
Thus far, I've only managed to create some sort of window into hell, where the "game" consists of unceasing violence, murder after murder after murder as towers of mismatched material swell and fall in ever transforming locations on the isle while the chat endlessly subscribes, spams, and emotes in cackling glee and the superimposed webcam video features a... thing with too many eyes and hands screaming incoherently.
At first I thought it was a problem with my dataset, so I started watching some of the streams myself.
This has not yielded insight into the whole "nightmare vision" output of my model, but it has expanded my vocabulary on the twin subjects of combustibles and comestibles, which I feel is a reasonable trade-off for the sanity battering associated with this whole endeavour.
If he was able to recall ~entire pages of the phone directory on command, I wonder if he could also recall (near) verbatim text of all the novels he had ever read, to what degree he could do this, or to what degree he could at least comprehensively recall key points, facts, timelines.
I would think he would have spent some time speculating on how the brain stores memories, I wonder if any of his theories were ever captured in some form.