基本信息
浏览量:94
职业迁徙
个人简介
At high level my main research question is: how can we integrate domain expert knowledge at the right abstraction level into machine learning (ML) systems and how can we extract knowledge from these systems at various abstraction levels.
In particular I have been interested in: 1) generalizing the type of information that ML algorithms can process and 2) extending the type of problems that ML can address.
1) The study of input generalization for ML algorithms has lead to the development of efficient and flexible graph kernels and feature generators for graphs (see the EDeN library) with applications in relational learning and chemo- and bioinformatics domains.
2) The study of generalizing ML tasks has lead to the notion of data driven design or Constructive Machine Learning (CML) (see the CML workshops). The objective of CML is the design of algorithms that can build novel objects endowed with desired properties. Such algorithms have a wide spectrum of applications, ranging from drug and protein design to automatic software generation, from music composition to video game assets construction.
In particular I have been interested in: 1) generalizing the type of information that ML algorithms can process and 2) extending the type of problems that ML can address.
1) The study of input generalization for ML algorithms has lead to the development of efficient and flexible graph kernels and feature generators for graphs (see the EDeN library) with applications in relational learning and chemo- and bioinformatics domains.
2) The study of generalizing ML tasks has lead to the notion of data driven design or Constructive Machine Learning (CML) (see the CML workshops). The objective of CML is the design of algorithms that can build novel objects endowed with desired properties. Such algorithms have a wide spectrum of applications, ranging from drug and protein design to automatic software generation, from music composition to video game assets construction.
研究兴趣
论文共 54 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Rolf Backofen,Fabrizio Costa,Fabian Theis,Carsten Marr,Martin Preusse,Claude Becker,Sita Saunders,Klaus Palme, Oleksandr Dovzhenko
INFORMATION- AND COMMUNICATION THEORY IN MOLECULAR BIOLOGYpp.85-100, (2018)
international joint conference on artificial intelligencepp.4183-4187, (2015)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn