AntoineSfx Posted January 15, 2022 Share Posted January 15, 2022 Say you have a network with a few parameters, and a value computed somewhere = the goal. In this example, it could be a grid, and edit to push some points upwards, and a Soft Radius distance. The grid is then subdivided and the distance to a sphere is measured for each. This is the goal to optimize. An algorithm to solve this is the Gradient descent. So we need to compute an approximation of the gradient of the goal and keep on tweaking the parameters in that direction (I'm talking about multi variable calculus here, i.e math) In Houdini, it looks like we're almost there with a For loop with a feedback to get the last computed goal. I'll sleep on it and see where it goes Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.