Compare several trees, bagged trees and the random forest.
0 datasets, 0 tasks, 0 flows, 0 runs
Based on three different tasks we want to compare three versions of ksvm - C-svc C classification - spoc-svc Crammer, Singer native multi-class - kbb-svc Weston, Watkins native multi-class
0 datasets, 0 tasks, 0 flows, 0 runs
none
0 datasets, 0 tasks, 0 flows, 0 runs
Paper on OpenML R library. Includes a case study on bagging vs forests
0 datasets, 0 tasks, 0 flows, 0 runs
An increase in undergraduate registered students in universities largely grown last years. However, the number of graduates remains low. The main cause of this issue is the evasion and / or retention…
0 datasets, 0 tasks, 0 flows, 0 runs
Data mining researchers and practitioners often use general rules of thumb or common data mining wisdom, those are so called data-mining myths. Even though, these myths are not always proven or…
0 datasets, 0 tasks, 0 flows, 0 runs
A subgroup discovery study.
0 datasets, 0 tasks, 0 flows, 0 runs
Almost every form of statistical and machine learning method has been applied to learning QSARs at one time or another: linear regression, decision trees, neural networks, nearest-neighbour methods,…
0 datasets, 0 tasks, 0 flows, 0 runs
The work will be submitted to ECML-PKDD2016
0 datasets, 0 tasks, 0 flows, 0 runs
Ensembles of classifiers are among the best performing classifiers available in many data mining applications. However, most ensembles developed specifically for the dynamic data stream setting rely…
0 datasets, 0 tasks, 0 flows, 0 runs
Example of collaborative research conducted by means of OpenML NB:
0 datasets, 0 tasks, 0 flows, 0 runs
No data.
0 datasets, 0 tasks, 0 flows, 0 runs
In this study, we investigate and summarize the performance of a wide range of ML algorithms (using its default hyper-parameter values) on a wide range of OpenML classifications tasks. This will yield…
0 datasets, 0 tasks, 0 flows, 0 runs
This study compares the local and global feature selection strategy on multilabel classification transformation methods
0 datasets, 0 tasks, 0 flows, 0 runs
The task of Quantitative Structure Activity Relationship (QSAR) Learning is to learn a function that, given the structure of a small molecule (a potential drug), outputs the predicted activity of the…
0 datasets, 0 tasks, 0 flows, 0 runs
One of the challenges in Machine Learning to find a classifier and parameter settings that work well on a given dataset. Evaluating all possible combinations typically takes too much time, hence many…
0 datasets, 0 tasks, 0 flows, 0 runs
We investigate the performance of a wide range of classification algorithms on a wide range of datasets to better understand when they perform well and when they don't. This will yield a meta-dataset…
512 datasets, 514 tasks, 63 flows, 91425 runs