User Tools

Site Tools


private:running_notes

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
private:running_notes [2019/12/27 21:27]
admin
private:running_notes [2019/12/27 21:28] (current)
admin
Line 9: Line 9:
   * Fast dropout (or any dropout) should zero mean the input - that way dropout doesn'​t change the weights.   * Fast dropout (or any dropout) should zero mean the input - that way dropout doesn'​t change the weights.
   * Values GAN (or classifier) - pain/​pleasure classifier on latent space, ​ use to guide the search when trying to solve a problem.   * Values GAN (or classifier) - pain/​pleasure classifier on latent space, ​ use to guide the search when trying to solve a problem.
-  * Take a space, second order decorrelate,​ model with BIC diagonal GMMs, expand as c_i * x_j, truncate those that are small, repeat until no signal left.  Inverse is to generate from latent/​noise model, apply inverse to get c_i * x_j, estiamte c_i, fill in missing from noise distribution,​ sum to get x_j and repeat downwards over.+  * Take a space, second order decorrelate,​ model with BIC diagonal GMMs, expand as c_i * x_j, truncate those that are small (as a fraction of signal power?), repeat until no signal left.  Inverse is to generate from latent/​noise model, apply inverse to get c_i * x_j, estiamte c_i, fill in missing from noise distribution,​ sum to get x_j and repeat downwards over.
  
  
private/running_notes.txt ยท Last modified: 2019/12/27 21:28 by admin