Difference between revisions of "Chang-Shing Lee"

From Chessprogramming wiki
Jump to: navigation, search
 
Line 8: Line 8:
 
=MogoTW=
 
=MogoTW=
 
Chang-Shing Lee is co-programmer of  the [[Go]] playing program ''MogoTW'' <ref>[http://www.computer-go.info/db/oprog.php?a=MogoTW MogoTW]</ref> <ref>[http://www.computer-go.info/db/operson.php?a=Lee%2C+Chang-Shing Details of Programmer: Lee, Chang-Shing - Co-programmer of MogoTW]</ref>, a joint project between the [https://www.game-ai-forum.org/icga-tournaments/program.php?id=515 MoGo] team and a Taiwanese team <ref>[http://www.lri.fr/~teytaud/mogo.html MoGo: a software for the Game of Go]</ref>. It shares code with MoGo.   
 
Chang-Shing Lee is co-programmer of  the [[Go]] playing program ''MogoTW'' <ref>[http://www.computer-go.info/db/oprog.php?a=MogoTW MogoTW]</ref> <ref>[http://www.computer-go.info/db/operson.php?a=Lee%2C+Chang-Shing Details of Programmer: Lee, Chang-Shing - Co-programmer of MogoTW]</ref>, a joint project between the [https://www.game-ai-forum.org/icga-tournaments/program.php?id=515 MoGo] team and a Taiwanese team <ref>[http://www.lri.fr/~teytaud/mogo.html MoGo: a software for the Game of Go]</ref>. It shares code with MoGo.   
 +
 +
=FML-based Prediction=
 +
Abtract from ''FML-based Prediction Agent and Its Application to Game of Go'' <ref>[[Chang-Shing Lee]], [[Mei-Hui Wang]], [[Chia-Hsiu Kao]], [[Sheng-Chi Yang]], [[Yusuke Nojima]], [[Ryosuke Saga]], [[Nan Shuo]], [[Naoyuki Kubota]] ('''2017'''). ''FML-based Prediction Agent and Its Application to Game of Go''. [https://arxiv.org/abs/1704.04719 arXiv:1704.04719]</ref>:
 +
In this paper, we present a robotic prediction agent including a [https://en.wikipedia.org/wiki/Darkforest darkforest] [[Go]] engine, a [https://en.wikipedia.org/wiki/Fuzzy_markup_language fuzzy markup language] (FML) assessment engine, an FML-based decision support engine, and a [[Robots|robot engine]] for game of Go application. The knowledge base and rule base of FML assessment engine are constructed by referring the information from the darkforest Go engine located in [https://en.wikipedia.org/wiki/National_University_of_Tainan NUTN] and [https://en.wikipedia.org/wiki/Osaka_Prefecture_University OPU], for example, the number of [[Monte-Carlo Tree Search|MCTS]] simulations and winning rate prediction. The proposed robotic prediction agent first retrieves the database of Go competition website, and then the FML assessment engine infers the winning possibility based on the information generated by darkforest Go engine. The FML-based decision support engine computes the winning possibility based on the partial game situation inferred by FML assessment engine. Finally, the robot engine combines with the human-friendly robot partner PALRO <ref>[https://palro.jp/en/ PALRO is a robot who cares]</ref>, produced by FujiSoft Incorporated, to report the game situation to human Go players. Experimental results show that the FML-based prediction agent can work effectively.
 +
 +
=PFML-based BCI Agent=
 +
Abtract from ''PFML-based Semantic BCI Agent for Game of Go Learning and Prediction'' <ref>[[Chang-Shing Lee]], [[Mei-Hui Wang]], [[Li-Wei Ko]], [[Bo-Yu Tsai]], [[Yi-Lin Tsai]], [[Sheng-Chi Yang]], [[Lu-An Lin]], [[Yi-Hsiu Lee]], [[Hirofumi Ohashi]], [[Naoyuki Kubota]], [[Nan Shuo]] ('''2019'''). ''PFML-based Semantic BCI Agent for Game of Go Learning and Prediction''. [https://arxiv.org/abs/1901.02999 arXiv:1901.02999]</ref>:
 +
This paper presents a semantic [https://en.wikipedia.org/wiki/Brain%E2%80%93computer_interface brain computer interface] (BCI) agent with [https://en.wikipedia.org/wiki/Particle_swarm_optimization particle swarm optimization] (PSO) based on a [https://en.wikipedia.org/wiki/Fuzzy_markup_language Fuzzy Markup Language] (FML) for [[Go]] [[Learning|learning]] and prediction applications.  Additionally, we also establish an Open Go [https://en.wikipedia.org/wiki/Darkforest Darkforest] (OGD) cloud platform with Facebook AI research (FAIR) open source Darkforest and ELF OpenGo AI bots <ref>[https://ai.facebook.com/blog/open-sourcing-new-elf-opengo-bot-and-go-research/ Open-sourcing a new ELF OpenGo bot and related Go research], February 13, 2019</ref>. The Japanese robot Palro will simultaneously predict the move advantage in the board game Go to the Go players for reference or learning. The proposed semantic BCI agent operates efficiently by the human-based BCI data from their [https://en.wikipedia.org/wiki/Neural_oscillation brain waves] and machine-based game data from the prediction of the OGD cloud platform for optimizing the parameters between humans and machines. Experimental results show that the proposed human and smart machine co-learning mechanism performs favorably. We hope to provide students with a better online learning environment, combining different kinds of handheld devices, robots, or computer equipment, to achieve a desired and intellectual learning goal in the future. 
  
 
=Selected Publications=
 
=Selected Publications=

Latest revision as of 15:07, 24 October 2019

Home * People * Chang-Shing Lee

Chang-Shing Lee [1]

Chang-Shing Lee,
a Taiwanese computer scientist and professor at National University of Tainan (NUTN). His major research interests are in ontology applications, knowledge management, capability maturity model integration (CMMI), semantic web, and artificial intelligence. He is also interested in intelligent agent, web services, fuzzy logic, genetic algorithm, and image processing. Chang-Shing Lee holds several patents on ontology engineering, document classificaton, image filtering and health care.

MogoTW

Chang-Shing Lee is co-programmer of the Go playing program MogoTW [2] [3], a joint project between the MoGo team and a Taiwanese team [4]. It shares code with MoGo.

FML-based Prediction

Abtract from FML-based Prediction Agent and Its Application to Game of Go [5]: 

In this paper, we present a robotic prediction agent including a darkforest Go engine, a fuzzy markup language (FML) assessment engine, an FML-based decision support engine, and a robot engine for game of Go application. The knowledge base and rule base of FML assessment engine are constructed by referring the information from the darkforest Go engine located in NUTN and OPU, for example, the number of MCTS simulations and winning rate prediction. The proposed robotic prediction agent first retrieves the database of Go competition website, and then the FML assessment engine infers the winning possibility based on the information generated by darkforest Go engine. The FML-based decision support engine computes the winning possibility based on the partial game situation inferred by FML assessment engine. Finally, the robot engine combines with the human-friendly robot partner PALRO [6], produced by FujiSoft Incorporated, to report the game situation to human Go players. Experimental results show that the FML-based prediction agent can work effectively.

PFML-based BCI Agent

Abtract from PFML-based Semantic BCI Agent for Game of Go Learning and Prediction [7]: 

This paper presents a semantic brain computer interface (BCI) agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for Go learning and prediction applications.  Additionally, we also establish an Open Go Darkforest (OGD) cloud platform with Facebook AI research (FAIR) open source Darkforest and ELF OpenGo AI bots [8]. The Japanese robot Palro will simultaneously predict the move advantage in the board game Go to the Go players for reference or learning. The proposed semantic BCI agent operates efficiently by the human-based BCI data from their brain waves and machine-based game data from the prediction of the OGD cloud platform for optimizing the parameters between humans and machines. Experimental results show that the proposed human and smart machine co-learning mechanism performs favorably. We hope to provide students with a better online learning environment, combining different kinds of handheld devices, robots, or computer equipment, to achieve a desired and intellectual learning goal in the future.

Selected Publications

[9]

2007 ...

2010 ...

Chang-Shing Lee, Mei-Hui Wang, Yu-Jen Chen, Shi-Jim Yen (2013). Apply Fuzzy Markup Language to Knowledge Representation for Game of Computer Go.

2015 ...

External Links

References

  1. ↑ Chang-Shing Lee | Ph. D. | National University of Tainan
  2. ↑ MogoTW
  3. ↑ Details of Programmer: Lee, Chang-Shing - Co-programmer of MogoTW
  4. ↑ MoGo: a software for the Game of Go
  5. ↑ Chang-Shing Lee, Mei-Hui Wang, Chia-Hsiu Kao, Sheng-Chi Yang, Yusuke Nojima, Ryosuke Saga, Nan Shuo, Naoyuki Kubota (2017). FML-based Prediction Agent and Its Application to Game of Go. arXiv:1704.04719
  6. ↑ PALRO is a robot who cares
  7. ↑ Chang-Shing Lee, Mei-Hui Wang, Li-Wei Ko, Bo-Yu Tsai, Yi-Lin Tsai, Sheng-Chi Yang, Lu-An Lin, Yi-Hsiu Lee, Hirofumi Ohashi, Naoyuki Kubota, Nan Shuo (2019). PFML-based Semantic BCI Agent for Game of Go Learning and Prediction. arXiv:1901.02999
  8. ↑ Open-sourcing a new ELF OpenGo bot and related Go research, February 13, 2019
  9. ↑ dblp: Chang-Shing Lee
  10. ↑ Fuzzy markup language (FML) from Wikipedia

Up one level

Retrieved from "https://www.chessprogramming.org/index.php?title=Chang-Shing_Lee&oldid=15278"