Kyoto University (京都大学) / 0048 / 新制・課程博士 / 博士(情報学) / 甲第19137号 / 情博第583号 / 新制||情||102 / 32088 / 京都大学大学院情報学研究科通信情報システム専攻 / (主査)教授 小野寺 秀俊, 教授 髙木 直史, 教授 佐藤 高史 / 学位規則第4条第1項該当

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第19137号 / 情博第583号 / 新制||情||102(附属図書館) / 32088 / 京都大学大学院情報学研究科通信情報システム専攻 / (主査)教授 小野寺 秀俊, 教授 髙木 直史, 教授 佐藤 高史 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

This master thesis is concerned about the resynthesis of combinational circuits with the help of evolutional principles. The first part of this text describes logic synthesis and its weak spots, evolutional synthesis and its advantages, and also some of the existing synthesis programs. The second part shows usage of graph algorithms in logic synthesis and their possible usage in an extension for the chosen synthesis program. Suggested design and practical implementation of the extension is also described in this part. In the third part extension testing is mentioned. The fourth part is the last one and concludes gained knowledge and results.

This master's thesis introduces the Random Boolean Networks as a developmental model in the evolutionary design. The representation of the Random Boolean Networks is described. This representation is combined with an evolutionary algorithm. The genetic operators are described too. The Random Boolean Networks are used as the developmental model for  the evolutionary design of the combinational circuits and the sorting networks. Moreover a representation of the Random Boolean Networks for the design of image filters is introduced. The proposed methods are evaluated in different case-studies. The results of the experiments are discussed together with the potential improvements  and topics of the next research.