Consciousness is not a computer program. Neurons don’t use binary. I’d love it if we had computers that could do squirrel things perfectly but we don’t even have that.
I can appreciate that contemporary neural networks are very different from organic intelligence, but consciousness is most definitely equivalent to a computer program. There are two things preventing us from reproducing it:
We don’t know nearly enough about how the human mind (or any mind, really) actually works, and
Our computers do not have the capacity to approximate consciousness with any meaningful degree of accuracy. Floating point representations of real numbers are not an issue (after all, you can always add more bits), but the sheer scale and complexity of the brain is a big one.
Also, for what it’s worth, most organic neurons actually do use binary (“one bit”) activation, while artificial “neurons” use a real-valued activation function for a variety of reasons, the biggest two being that (a) training algorithms require differentiable models, and (b) binary activation functions do not yield a lot of information per neuron while requiring effectively the same amount of memory.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.world
This is a most excellent place for technology news and articles.
Consciousness is not a computer program. Neurons don’t use binary. I’d love it if we had computers that could do squirrel things perfectly but we don’t even have that.
Binary neurons are still neurons
I can appreciate that contemporary neural networks are very different from organic intelligence, but consciousness is most definitely equivalent to a computer program. There are two things preventing us from reproducing it:
Also, for what it’s worth, most organic neurons actually do use binary (“one bit”) activation, while artificial “neurons” use a real-valued activation function for a variety of reasons, the biggest two being that (a) training algorithms require differentiable models, and (b) binary activation functions do not yield a lot of information per neuron while requiring effectively the same amount of memory.