Re:Consciousness is a recurrent neural network
by amelius on Thursday November 24, 2016 @10:45AM
(#13030868)
Ok, so would an algorithm that uses genetic programming have a consciousness like we do? Would it be capable of feeling pain?
This is what I'm interested in, but what the theory presented here fails to explain.
Re:Consciousness is a recurrent neural network
by visarga on Thursday November 24, 2016 @12:08PM
(#13031333)
It would be able to feel pain if it can learn to avoid it. In humans, pain, hunger and other emotions are just reward signals that guide behavior such that we don't die.
It would also need to be embodied and responsible for its own survival, more generally, otherwise it's just a computer running software, in a lack of external context.
Pleasure and pain are related to reward signalling in reinforcement learning. Humans have inborn reward signals which have been selected by evolution. Artificial agents have reward signals too, but they are designed.
So I think the path to consciousness is to create artificial agents that learn to survive and adapt. When such a complex behavioral system is designed, it naturally learns about its relation to the world. It has consciousness by extension of being capable to protect its life.