About: A collection of python code to perform research in optimization. The aim is to provide reusable components that can be quickly applied to machine learning problems. Used in: - Ellipsoidal multiple instance learning - difference of convex functions algorithms for sparse classfication - Contextual bandits upper confidence bound algorithm (using GP) - learning output kernels, that is kernels between the labels of a classifier.

• minor bugfix

About: The source code of the mldata.org site - a community portal for machine learning data sets.

Initial Announcement on mloss.org.

About: Tools to convert datasets from various formats to various formats, performance measures and API functions to communicate with mldata.org

• Change task file format, such that data splits can have a variable number items and put into up to 256 categories of training/validation/test/not used/...
• Various bugfixes.

About: This is the source code of the mloss.org website.

Now works with newer django versions and fixes several warnings and minor bugs underneath. The only user visible change is probably that the subscription and bookmark buttons work again.

About: The Easysvm package provides a set of tools based on the Shogun toolbox allowing to train and test SVMs in a simple way.

Fixes for shogun 0.7.3.

About: The goal of this project is to provide code for reading and writing machine learning data sets for as many programming languages as possible.

Forgot to include the Java sources.

About: We provide some preliminary code for multiclass multiple kernel learning in Matlab using CPLEX as a base solver.

Initial Announcement on mloss.org.

About: PALMA computes the optimal spliced alignment of a mRNA sequence to a genomic sequence. The main python script takes two FASTA files containing the target (e.g. a DNA sequence, part of the genome) [...]

Initial Announcement on mloss.org.