Changes

Jump to: navigation, search

Matthias Lüscher

20 bytes added, 11:03, 19 June 2018
no edit summary
'''Matthias Lüscher''',<br/>
a Swiss computer scientist and senior technology engineer. He holds a diplom degree in computerized sciences <ref>[https://www.ethz.ch/de/studium/bachelor/studienangebot/naturwissenschaften-und-mathematik/rechnergestuetzte-wissenschaften/was-ist.html Was sind Rechnergestützte Wissenschaften? | ETH Zürich]</ref> from [[ETH Zurich]], and is author of the chess engine [[Chessterfield]]. Inspired by [[Michael Buro|Michael Buro's]] [[CG 1998]] paper ''From Simple Features to Sophisticated Evaluation Functions'' <ref>[[Michael Buro]] ('''1998'''). ''[http://link.springer.com/chapter/10.1007/3-540-48957-6_8 From Simple Features to Sophisticated Evaluation Functions]''. [[CG 1998]], [https://skatgame.net/mburo/ps/glem.pdf pdf]</ref>, covering not only [[Automated Tuning|automated parameter tuning]] but a procedure for exploring the feature space able to discover new features in a computational feasible way, Matthias Lüscher implemented Buro's ''[[Michael Buro#GLEM|General Linear Evaluation Model'' ]] (GLEM ) inside the experimental chess program ''ChessterfieldCL'', using a three-layer [[Neural Networks|neural network]] as [[Evaluation|evaluation function]], as documented in his technical report under supervision of [[Thomas Lincke]] and [[Christoph Wirth]] <ref>[[Matthias Lüscher]] ('''2000'''). ''Automatic Generation of an Evaluation Function for Chess Endgames''. [[ETH Zurich]] Supervisors: [[Thomas Lincke]] and [[Christoph Wirth]], [http://www.datacomm.ch/m.luescher/evaluation_function_en.pdf pdf], [http://www.top-5000.nl/ps/Automatic%20Generation%20of%20an%20Evaluation%20Function%20for%20Chess%20Endgames.pdf pdf]</ref>.
=Publications=

Navigation menu