Skip to content
forked from lawrennd/optimi

MATLAB helper functions and constraint functions for optimization.

Notifications You must be signed in to change notification settings

SheffieldML/optimi

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Matlab Optimi Toolbox

This page describes the optimi toolbox for MATLAB available for download here.

Dependencies

The optimi toolbox depends on

  • ndlutil various utility functions.

Release Information

Current release is 0.132.

Included a function to return the default functions to be used for particular constraints and a function to return the default optimiser.

Added wrappers for using Carl Rasmussen's conjugate gradient code.

This toolbox allows computation of several different non-linearities and associated conversions and their gradients.

There are several kernels implemented, the ones that are being maintained for the latest release are:

exp sigmoid negLogLogit

exp constrains a parameter to be positive through exponentiatiation. sigmoid constrains a parameter to be between 0 and 1 through the sigmoid function and negLogLogit constrains a parameter to be positive through the function log(1+exp(x)). In much of the code based on this we prefer negLogLogit to exp as it is better behaved for large x.

Page last modified on Fri Jan 5 22:19:06 GMT 2007.

About

MATLAB helper functions and constraint functions for optimization.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MATLAB 100.0%