I haven’t read through the parent post yet, but I’m excited to do so tonight for almost precisely this reason.
It feels like markets, neural networks, evolution, human organizational hierarchies, and any number of other systems resolve into some common structure, with individual agents performing some computation, passing around some summary messages, and then thriving or diminishing based on the system’s performance on some task.
I’d be interested in an underlying mathematical model that unifies many of these fields. A mapping between natural selection and gradient descent is a useful piece of that puzzle.
I haven’t read through the parent post yet, but I’m excited to do so tonight for almost precisely this reason.
It feels like markets, neural networks, evolution, human organizational hierarchies, and any number of other systems resolve into some common structure, with individual agents performing some computation, passing around some summary messages, and then thriving or diminishing based on the system’s performance on some task.
I’d be interested in an underlying mathematical model that unifies many of these fields. A mapping between natural selection and gradient descent is a useful piece of that puzzle.
The Price equation :)
Thanks for the pointer! Looks like I’ve got my reading assignments lined up :-).