Jump to content

Optimize the parameters of a network to maximize a goal

Recommended Posts

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


Link to comment
Share on other sites

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.

Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

  • Create New...