Deep Learning and Reinforcement Learning at BIOMA'2020

Veröffentlicht: von & gespeichert unter Conference/Journal paper, General, Optimization, Publications, Reinforcement Learning, Research, Research Projects

We are happy to announce that the CIOP group of TH Köln participated with two papers and two talks at the 9th International Conference BIOMA'2020 (Bioinspired Optimization Methods and Applications), which took place November 2020, 19th-20th, and was this year a completely online event: "Reinforcement Learning for N-Player Games: The Importance of Final Adaptation" by...

TH Köln takes part in AI Graduate College Data-NInJA

Veröffentlicht: von & gespeichert unter General, Reinforcement Learning, Research, Research Projects

The State of North Rhine-Westphalia provides a grant for the AI Graduate College Data-NInJA („Trustworthy AI for Seamless Problem Solving: Next Generation Intelligence Joins Robust Data Analysis“), coordinated by Prof. Barbara Hammer, University Bielefeld. The grant consists of seven PhD tandems, which were selected out of 37 applications for this grant by an expert jury. TH...

Opitz Reward for Bachelor Thesis about AI and Music

Veröffentlicht: von & gespeichert unter Bachelor/Master Thesis, General, Research

Jordan Scholzen got with his Bachelor's thesis "Künstliche Intelligenz in der Kompositionslehre - Eine Untersuchung von Long-Short-Term-Memory-Netzen zur Analyse von Kontrapunkten nach Fux" the first place in the Opitz-Innovation Reward 2020. The thesis, supervised by Prof. Dr. Wolfgang Konen, investigates how a supportive AI for music scholars studying composition can look like. Scholzen showed that...

First Fully-Online PhD-Colloquium at Leiden University

Veröffentlicht: von & gespeichert unter General, MONREP, Research

I am very happy to announce that on Wednesday, April 8th 2020, the PhD-colloquium of Samineh Bagheri, which I had the honor to supervise at TH Köln, successfully took place. Her thesis “Self-Adjusting Surrogate-Assisted Optimization Techniques for Expensive Constrained Black Box Problems” deals with state-of-the art optimization algorithms supported by RBF surrogate models.  In normal...

TDMR 2.0 now available on CRAN

Veröffentlicht: von & gespeichert unter General

The R package TDMR (Tuned Data Mining in R) is now available on CRAN in a major new release 2.0. It supports the new R  package SPOT 2.0 (Sequential Parameter Optimization Toolbox) with its largely redesigned and simplified interface. TDMR 2.0 has as well a simplified interface. TDMR documentation and TDMR tutorials have been rewritten...

Free download of our ASOC Article until November, 02, 2017

Veröffentlicht: von & gespeichert unter Conference/Journal paper, General, MONREP, Optimization, Publications

If you are interested in our recent article Self-adjusting parameter control for surrogate-assisted constrained optimization under limited budgets  which appeared in the journal Applied Soft Computing (ASOC), please take the opportunity to follow this link: For a period until November, 02, 2017, this link will provide the free download of the final journal article....

TDMR 1.5 Available For Download Here

Veröffentlicht: von & gespeichert unter Data Mining, Research, SOMA

Due to a major release change in SPOT, the newest package version SPOT 2.0 on CRAN is currently not compatible with TDMR 1.5 (and TDMR 1.4). Therefore TDMR is currently archived on CRAN. We are working on an update. For the time being: You can download TDMR 1.5 (and 1.4) together with the last compatible...

Young Author Award for Samineh Bagheri

Veröffentlicht: von & gespeichert unter General, MONREP, Optimization, Research

The 25th Workshop Computational Intelligence 2015, an annual conference held in Nov'2015 by the Computational Intelligence (CI) Chapter of VDI-GMA (Gesellschaft für Mess- und Automatisierungstechnik) in Dortmund, has attributed the Young Author Award to Samineh Bagheri, PhD, scientific member of the research group of Professor Konen at Campus Gummersbach. Congratulations!

New Technical Report on Temporal Difference Learning for Games

Veröffentlicht: von & gespeichert unter General, Publications, Reinforcement Learning, Research

A new technical report on temporal difference (TD) learning for games and "self-play" algorithms for game-agent training is available. This report by Wolfgang Konen features a gentle introduction to TD learning for game play and gives hints for the practioner on the implementation of such algorithms . It shows the references to the most recent...