Bestand wählen
Filter anzeigen Filter ausblenden

Suche eingrenzen

1-4 von 4 Ergebnissen
Anzeige anpassen
  • Sortieren nach:
55:49 Vanschoren, Joaquin Englisch 2014

Meta-Learning on QSAR data

Can we learn how to design drugs? Topics include: Automating drug discovery with the Robot Scientist. Using chemoinformatic databases and in-house datasets to systematically run extensive comparative QSAR experiments. Learning how to better apply existing QSAR methods. Decreasing the time and cost to develop new drugs. Prof. Dr. Ross D. King is Professor of Machine Intelligence in the School of Computer Science at the University of Manchester. King's research interests are in the automation of science, drug design, AI, machine learning and synthetic biology. He is probably best known for the Robot Scientist.
  • Erscheinungsjahr: 2014
  • Herausgeber: Vanschoren, Joaquin
  • Sprache: Englisch
46:58 Vanschoren, Joaquin Englisch 2014

Estimating the Performance of Predictive Models in R

This talk will start with a very brief introduction to R and the main concepts of this data analysis environment and programming language. We will then shift focus to predictive tasks and models obtained from data to solve these tasks. Finally, the main topic of the talk will be on how to solve the critical issue of estimating the predictive performance of alternative models to solve some task. This estimation process is key to answer the question of which model is the "best" for a problem we are facing. We will describe the facilities provided by the R package performanceEstimation to address this model selection problem and provide some illustrative case studies. We wrap up with the ongoing plans of interfacing this package to OpenML.
  • Erscheinungsjahr: 2014
  • Herausgeber: Vanschoren, Joaquin
  • Sprache: Englisch
41:15 Vanschoren, Joaquin Englisch 2014

OpenML, R, mlr

I will first introduce an R package to interface with OpenML. We support querying and downloading, running experiments and uploading results, so that all your experiments are organized online. R itself allows many forms of machine learning methods and experiments, from completely custom code to powerful semi-automated frameworks. The OpenML package is framework-agnostic in that regard. The mlr package provides a generic, object-oriented, and extensible interface to a large number of machine learning methods in R. It enables researchers and practitioners to easily compare methods and implementations from different packages, rapidly conduct complex experiments, and implement their own meta-methods using mlr's building blocks. Classification, regression, survival analysis, and clustering are supported and virtually every resampling strategy. Meta-Optimization can be performed by tuning, feature filtering and feature selection, and most modeling steps can be parallelized. Its object-oriented structure provides in many cases a close match to the OpenML structure, and it can already be connected to the OpenML R package in a simple manner. The talk will conclude with an outlook regarding the next steps, open challenges and ideas to improve upon the current state of the project.
  • Erscheinungsjahr: 2014
  • Herausgeber: Vanschoren, Joaquin
  • Sprache: Englisch
35:52 Joaquin Vanschoren Englisch 2014

OpenML: Open, Networked Machine Learning

Today, the ubiquity of the internet is allowing new, more scalable forms of scientific collaboration. Networked science uses online tools to share and organize data on a global scale so that scientists are able to build directly on each other's data and techniques, reuse them in unforeseen ways, and mine all data to search for patterns. OpenML.org is a place where researchers can easily share and reuse machine learning data sets, tools and experiments. It helps researchers win time by automating machine learning experiments as much as possible, and gain more credit for their work by making it more visible and easily reusable. Moreover, OpenML helps scientists and students to explore different machine learning techniques, find out which are most useful in their work, and collaborate with others to analyze scientific data online.
  • Erscheinungsjahr: 2014
  • Herausgeber: Joaquin Vanschoren
  • Sprache: Englisch
von 1 Seiten
Loading...
Feedback