does this mean i get to fuck robots
What should be sex for AI?
11–14 of 14 posts
Re: What should be sex for AI?
#12Earlier quoted context omitted.
Yes, you suggest a little effective training method. What I suggest is training a lot of very little effective training methods looking for mutations. By not being gready perhaps AI can develop a new system for evolving that we can't envision at this moment.
Just to be a little more concrete: What about a "genetic algorithm" approach for a population in which individuals are genetic algorithms and in which the optimization function put a great weight on being self-sustainability and diversity of structure.
That reminds me of the idea of training a neural net to express a function that, if used where the sigmoid function would be used in a neural net, would result in the neural networks using it being trained well and quickly.
I assumed training a neural net like that would be too expensive (each evaluation of it would require training a neural net), for not much benefit (I don't expect the result to be better than the sigmoid function).
I'm not sure quite what you mean by self-sustainability. What does it mean for a genetic-like algorithm to be self-sustainable?
This idea also sounds like it would be very computationally expensive, but it's possible I misunderstand.
If it could be modified to only use one layer of these algorithms, maybe that would be less expensive?
I am imagining neural nets that each do both image to label, and label to image, where I guess they would engage in a sort of challenge response thing, where one produces a label and requests an image, and evaluates the image received, and provides an image and requests a label (or level of confidence for each label) and evaluates the response, and then when both have evaluated the responses, they output whether or not to reproduce, and if both do, then the genetic part is done. Sort of like a mating dance I guess. (Of course, what challenges and responses they give, and whether they accept, would also be determined by things that are recombined like the other stuff.)
But having that by itself wouldn't be enough, because it needs some connection to real things in order for the "image recognition" to represent anything real. There has to be some sort of real fitness for the reproductive fitness evaluation for the bots to evaluate.
Idk how much that fits with your idea.
Re: What should be sex for AI?
#13Earlier quoted context omitted.
Just to be a little more concrete: What about a "genetic algorithm" approach for a population in which individuals are genetic algorithms and in which the optimization function put a great weight on being self-sustainability and diversity of structure.
That reminds me of the idea of training a neural net to express a function that, if used where the sigmoid function would be used in a neural net, would result in the neural networks using it being trained well and quickly. I assumed training a neural net like that would be too expensive (each evaluation of it would require training a neural net), for not much benefit (I don't expect the result to be better than the…
The mating dance and the need of some sort of real fitness is interesting. By self-sustainability I was thinking about some form of interactions with the property to not become blocked or extinguished easily, some property to overcome problems, filter agents that don't satisfy certain interesting properties.
Re: What should be sex for AI?
#14the purpose of sex in biological systems is to speed up the rate of genetic change and introduce mutation at a faster rate, there is no reason why Genetic Algorithms couldn't fill this void, OR have two programs collaborate on a set of goals, (i.e. two programs acts as checks and balances for the design of some other program that solves a goal that both parent program understand; (i.e understand not reason about), at that point though, that wouldn't be 'sex', that would just be a collaboration of two programs. Example, two ruby programs get together and write a C program, that in turn could collaborate with the two ruby programs to design and create a 4th program; and perhaps in a different language.)