3 projects found that use the lgpl version 3 or later license.


Logo libcmaes 0.9.1

by beniz - October 9, 2014, 10:08:18 CET [ Project Homepage BibTeX Download ] 1766 views, 375 downloads, 3 subscriptions

About: Libcmaes is a multithreaded C++11 library (with Python bindings) for high performance blackbox stochastic optimization of difficult, possibly non-linear and non-convex functions, using the CMA-ES algorithm for Covariance Matrix Adaptation Evolution Strategy. Libcmaes is useful to minimize / maximize any function, without information regarding gradient or derivability.

Changes:

Small release with two bug fixes and tiny changes otherwise:

  • small API improvements

  • fixed bug in tolX stopping criteria when using 'sep' algorithm

  • fixed bug to the natural gradient with genotype /phenotype transforms

  • file stream now outputs parameter's mean in phenotype

  • tiny wrapper to simplify maximization of objective function (default is minimization)


Logo Crino 1.0.0

by jlerouge - July 16, 2014, 17:54:55 CET [ Project Homepage BibTeX Download ] 615 views, 135 downloads, 2 subscriptions

About: Crino: a neural-network library based on Theano

Changes:

1.0.0 (7 july 2014) : - Initial release of crino - Implements a torch-like library to build artificial neural networks (ANN) - Provides standard implementations for : * auto-encoders * multi-layer perceptrons (MLP) * deep neural networks (DNN) * input output deep architecture (IODA) - Provides a batch-gradient backpropagation algorithm, with adaptative learning rate


Logo MIToolbox 2.1

by apocock - June 30, 2014, 01:05:57 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 13338 views, 2518 downloads, 1 subscription

About: A mutual information library for C and Mex bindings for MATLAB. Aimed at feature selection, and provides simple methods to calculate mutual information, conditional mutual information, entropy, conditional entropy, Renyi entropy/mutual information, and weighted variants of Shannon entropies/mutual informations. Works with discrete distributions, and expects column vectors of features.

Changes:

Added weighted entropy functions. Fixed a few memory handling bugs.