Yes I am thinking that disconnecting is not the issue but if a leared mechanism to auto adjust to shut off redundancies could be practical. Sort of learned self optimalization.
But before even considering such developing is more the key.
Still such if at a point were possible it would be one hell of a leap forward, even improving on organic models.
You discuss building an ever increasing complexity of connections. Has thought been given to the extinction of what inevitably will become, in some cases, redundant connections? This could streamline process and reduce power consumption.
In organic intelligence the extinction of neural connections is incredibly slow, hence one of the key issues in addiction recovery for example. Unlearning is hard, much harder than learning but oft is required. Could an ability to maximize efficiecy by discarding redundant connections be built in? But, perhaps this is putting the cart before the horse, or indeed the mere concept of an embryonic horse to be a more accurate metaphore.
Yes! Often redundant connection can be switched off, and allow to be switched back on in the future, but I'm thinking more and more about how removing neurons may be beneficial.
when it comes to the efficiency of un-learning, I am unsure. As I'm sure you know complex tasks or behaviours require a multitude of neurons to fire in order to complete the operation. So the problem would shift from figuring out how to weaken connections to how to locate which connections need to turned off.
Yes I am thinking that disconnecting is not the issue but if a leared mechanism to auto adjust to shut off redundancies could be practical. Sort of learned self optimalization.
But before even considering such developing is more the key.
Still such if at a point were possible it would be one hell of a leap forward, even improving on organic models.
But I get ahead of myself.
Thanks for the thought :D
A thought has occured to me.
You discuss building an ever increasing complexity of connections. Has thought been given to the extinction of what inevitably will become, in some cases, redundant connections? This could streamline process and reduce power consumption.
In organic intelligence the extinction of neural connections is incredibly slow, hence one of the key issues in addiction recovery for example. Unlearning is hard, much harder than learning but oft is required. Could an ability to maximize efficiecy by discarding redundant connections be built in? But, perhaps this is putting the cart before the horse, or indeed the mere concept of an embryonic horse to be a more accurate metaphore.
Yes! Often redundant connection can be switched off, and allow to be switched back on in the future, but I'm thinking more and more about how removing neurons may be beneficial.
when it comes to the efficiency of un-learning, I am unsure. As I'm sure you know complex tasks or behaviours require a multitude of neurons to fire in order to complete the operation. So the problem would shift from figuring out how to weaken connections to how to locate which connections need to turned off.