Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Consciousness is a recurrent neural network

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 50 posts

Re: Consciousness is a recurrent neural network

#41

Post by rayalez »

dghf wrote: post #20
rayalez wrote: post #8

Great explanation, makes perfect sense to me! My own heory is pretty much the same. Just like you can experience other internal sensations in your body when nerves send signals that are recognized by the brain, the brain can recognize it's own signals. I highly recommend to read Godel Escher Bach(if you dont have time - just read the introduction to get the general idea). In this book author explains how the meaning…

> I highly recommend to read Godel Escher Bach(if you dont have time - just read the introduction to get the general idea). I don't think you'll get any real sense of what GEB is about just by reading the introduction.

Well, duh doi. What I mean is that the introduction gave me the epiphany related to the concept I'm talking about, and if you're not ready to commit a ton of time to reading the whole book, you should still read the intro, because it explains a lot of awesome things related to the OP's post.

But you're right, the whole book does contain more information than it's first few pages. No shit.

Re: Consciousness is a recurrent neural network

#42

Post by wbhart »

hacker_9 wrote: post #38
wbhart wrote: post #9

Can't the same argument be used to show that consciousness is a whole bunch of things that it clearly is not. Just arguing that consciousness has certain attributes and it shares those attributes with something else, doesn't make consciousness an example of that something else. I think there is a general trend towards thinking of consciousness as an emergent phenomenon which exists when a system is complex enough and…

Well we know the brain is incredibly advanced, as evolution has had a lot of time to work on it. It could be that to make something conscious just requires a very complex physical procedure or set of interconnected components. Once humans became conscious, it then worked out to be evolutionary beneficial to remain conscious in future generations. To me, to be 'conscious' is to be able to make decisions. Presented wit…

It seems to me that a meteorological expert system is conscious by that definition. I find that dubious.

Re: Consciousness is a recurrent neural network

#43

Post by RivieraKid »

andybak wrote: post #19

I have a tongue-in-cheek theory: Those who think there's not a "hard problem of consciousness" or hand-wave it away with purely materialist explanations probably aren't conscious. Folks. We have p-zombies in our midst...

Yeah, I sometimes use this as an "argument", but don't actually believe this.

Re: Consciousness is a recurrent neural network

#44

Post by hacker_9 »

wbhart wrote: post #42
hacker_9 wrote: post #38

Earlier quoted context omitted.

Well we know the brain is incredibly advanced, as evolution has had a lot of time to work on it. It could be that to make something conscious just requires a very complex physical procedure or set of interconnected components. Once humans became conscious, it then worked out to be evolutionary beneficial to remain conscious in future generations. To me, to be 'conscious' is to be able to make decisions. Presented wit…

It seems to me that a meteorological expert system is conscious by that definition. I find that dubious.

An expert system doesn't actually make decisions; the programmers made the decisions and then hard coded them in. Something along the lines of 'if (wind_pressure > 0 && rain_density < 0.5) do_something() else etc'. It's probably a bit more dynamic than that, but however you do it, it is always the programmers that make the decisions and then write them in, to be replayed by the software later with different variables.

Re: Consciousness is a recurrent neural network

#45

Post by dwaltrip »

hasenj wrote: post #10

The problem with this line of thinking is that any data model for anything has absolutely no intrinsic meaning. It's just an encoding. To give the simplest example: you can model a color in many different encodings, 'red', 'hsl(0, 50%, 50%)', 'rgb(255, 0, 0)', etc. Any "thing" can be encoded in an infinitely different number of ways. The same applies to the state of your mind. Why should one encoding give rise to con…

Computers don't model much at all, let alone themselves. They run static, one-off code that was fed to them by external sources, and contain no coherent, dynamic models of real world systems. My dog models more of the world than any computer we've yet built.

Sure, some computer programs model specific things quite well. But these models are very limited, fixed, and useless without human interpretation.

Re: Consciousness is a recurrent neural network

#47

Post by hasenj »

dwaltrip wrote: post #45
hasenj wrote: post #10

The problem with this line of thinking is that any data model for anything has absolutely no intrinsic meaning. It's just an encoding. To give the simplest example: you can model a color in many different encodings, 'red', 'hsl(0, 50%, 50%)', 'rgb(255, 0, 0)', etc. Any "thing" can be encoded in an infinitely different number of ways. The same applies to the state of your mind. Why should one encoding give rise to con…

Computers don't model much at all, let alone themselves. They run static, one-off code that was fed to them by external sources, and contain no coherent, dynamic models of real world systems. My dog models more of the world than any computer we've yet built. Sure, some computer programs model specific things quite well. But these models are very limited, fixed, and useless without human interpretation.

> these models are very limited, fixed, and useless without human interpretation.

What model _isn't_ useless without human interpretation?

Re: Consciousness is a recurrent neural network

#48

Post by dwaltrip »

hasenj wrote: post #47
dwaltrip wrote: post #45

Earlier quoted context omitted.

Computers don't model much at all, let alone themselves. They run static, one-off code that was fed to them by external sources, and contain no coherent, dynamic models of real world systems. My dog models more of the world than any computer we've yet built. Sure, some computer programs model specific things quite well. But these models are very limited, fixed, and useless without human interpretation.

> these models are very limited, fixed, and useless without human interpretation. What model _isn't_ useless without human interpretation?

The models of the world inside the brain of many different animals. They sustain themselves

Even the models of the world in our own brains are not fully known to us, and we largely make use of them without interpretation.

Basically, any model that wasn't created by humans does not need human interpretation.

Re: Consciousness is a recurrent neural network

#49

Post by hasenj »

dwaltrip wrote: post #48
hasenj wrote: post #47

Earlier quoted context omitted.

> these models are very limited, fixed, and useless without human interpretation. What model _isn't_ useless without human interpretation?

The models of the world inside the brain of many different animals. They sustain themselves Even the models of the world in our own brains are not fully known to us, and we largely make use of them without interpretation. Basically, any model that wasn't created by humans does not need human interpretation.

That's a circular argument. You're just assuming that these models have intrinsic meaning.
Post reply on HN