This site uses cookies to improve your experience. To help us insure we adhere to various privacy regulations, please select your country/region of residence. If you do not select a country, we will assume you are from the United States. Select your Cookie Settings or view our Privacy Policy and Terms of Use.
Cookie Settings
Cookies and similar technologies are used on this website for proper function of the website, for tracking performance analytics and for marketing purposes. We and some of our third-party providers may use cookie data for various purposes. Please review the cookie settings below and choose your preference.
Used for the proper function of the website
Used for monitoring website traffic and interactions
Cookie Settings
Cookies and similar technologies are used on this website for proper function of the website, for tracking performance analytics and for marketing purposes. We and some of our third-party providers may use cookie data for various purposes. Please review the cookie settings below and choose your preference.
Strictly Necessary: Used for the proper function of the website
Performance/Analytics: Used for monitoring website traffic and interactions
But it really wasn’t physics, or computerscience, or math, or biology, or economics, or any known field. The idea not of solving equations, but instead of setting up computational rules that could be explicitly run to represent and reproduce things in the world. What is that science? But at least it would have a home.
Because it implies that whatever “computational parametrization” or “computational description language” one uses for the ruliad, one will almost always get something that can be viewed as “computationally equivalent”. But what about other models of computation—like cellular automata or register machines or lambda calculus?
And if we’re going to make a “general theory of mathematics” a first step is to do something like we’d typically do in naturalscience, and try to “drill down” to find a uniform underlying model—or at least representation—for all of them. From a computerscience perspective, we can think of it as being like a type hierarchy.
It’s not obvious that it would be feasible to find the path of the steepest descent on the “weight landscape” But calculus comes to the rescue. As we mentioned above, one can always think of a neural net as computing a mathematical function—that depends on its inputs, and its weights.
We organize all of the trending information in your field so you don't have to. Join 28,000+ users and stay up to date on the latest articles your peers are reading.
You know about us, now we want to get to know you!
Let's personalize your content
Let's get even more personalized
We recognize your account from another site in our network, please click 'Send Email' below to continue with verifying your account and setting a password.
Let's personalize your content