FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1938185710> ?p ?o ?g. }

• W1938185710 abstract "This thesis is concerned with the problem of learning comprehensible theories from structured data and covers primarily classification and regression learning. The basic knowledge representation language is set around a polymorphically-typed, higherorder logic. The general setup is closely related to the learning from propositionalized knowledge and learning from interpretations settings in Inductive Logic Programming. Individuals (also called instances) are represented as terms in the logic. A grammar-like construct called a predicate rewrite system is used to define features in the form of predicates that individuals may or may not satisfy. For learning, decisiontree algorithms of various kinds are adopted. The scope of the thesis spans both theory and practice. On the theoretical side, I study in this thesis 1. the representational power of different function classes and relationships between them; 2. the sample complexity of some commonly-used predicate classes, particularly those involving sets and multisets; 3. the computational complexity of various optimization problems associated with learning and algorithms for solving them; and 4. the (efficient) learnability of different function classes in the PAC and agnostic PAC models. On the practical side, the usefulness of the learning system developed is demontrated with applications in two important domains: bioinformatics and intelligent agents. Specifically, the following are covered in this thesis: 1. a solution to a benchmark multiple-instance learning problem and some useful lessons that can be drawn from it; 2. a successful attempt on a knowledge discovery problem in predictive toxicology, one that can serve as another proof-of-concept that real chemical knowledge can be obtained using symbolic learning; 3. a reworking of an exercise in relational reinforcement learning and some new insights and techniques we learned for this interesting problem; and 4. a general approach for personalizing user agents that takes full advantage of symbolic learning." @default.
• W1938185710 created "2016-06-24" @default.
• W1938185710 creator A5048997284 @default.
• W1938185710 date "2005-10-01" @default.
• W1938185710 modified "2023-09-23" @default.
• W1938185710 title "Learning Comprehensible Theories from Structured Data" @default.
• W1938185710 cites W100909291 @default.
• W1938185710 cites W116380033 @default.
• W1938185710 cites W1480376833 @default.
• W1938185710 cites W1485997076 @default.
• W1938185710 cites W1486312284 @default.
• W1938185710 cites W148834693 @default.
• W1938185710 cites W1488498023 @default.
• W1938185710 cites W1490466294 @default.
• W1938185710 cites W1492170170 @default.
• W1938185710 cites W1497782867 @default.
• W1938185710 cites W1504694836 @default.
• W1938185710 cites W1504808146 @default.
• W1938185710 cites W150885707 @default.
• W1938185710 cites W1514468887 @default.
• W1938185710 cites W1517151294 @default.
• W1938185710 cites W1517178556 @default.
• W1938185710 cites W1520252399 @default.
• W1938185710 cites W1535599202 @default.
• W1938185710 cites W1537312987 @default.
• W1938185710 cites W1541434994 @default.
• W1938185710 cites W1542886316 @default.
• W1938185710 cites W1543252775 @default.
• W1938185710 cites W1545331097 @default.
• W1938185710 cites W1546703439 @default.
• W1938185710 cites W1554663460 @default.
• W1938185710 cites W156056545 @default.
• W1938185710 cites W1563088657 @default.
• W1938185710 cites W1565236324 @default.
• W1938185710 cites W1571076699 @default.
• W1938185710 cites W1571502146 @default.
• W1938185710 cites W1573772481 @default.
• W1938185710 cites W1576452626 @default.
• W1938185710 cites W1584815367 @default.
• W1938185710 cites W1591356244 @default.
• W1938185710 cites W1591425247 @default.
• W1938185710 cites W1594031697 @default.
• W1938185710 cites W1603305011 @default.
• W1938185710 cites W1605089207 @default.
• W1938185710 cites W1606033961 @default.
• W1938185710 cites W1606272177 @default.
• W1938185710 cites W1608131845 @default.
• W1938185710 cites W161969897 @default.
• W1938185710 cites W1633338417 @default.
• W1938185710 cites W1640646391 @default.
• W1938185710 cites W1647622147 @default.
• W1938185710 cites W1666090206 @default.
• W1938185710 cites W1676820704 @default.
• W1938185710 cites W1731670240 @default.
• W1938185710 cites W1848110409 @default.
• W1938185710 cites W1881647329 @default.
• W1938185710 cites W1918179283 @default.
• W1938185710 cites W1938103548 @default.
• W1938185710 cites W1946852907 @default.
• W1938185710 cites W1966280301 @default.
• W1938185710 cites W1969223365 @default.
• W1938185710 cites W1970074386 @default.
• W1938185710 cites W1973631422 @default.
• W1938185710 cites W1975846642 @default.
• W1938185710 cites W1983168840 @default.
• W1938185710 cites W1987902506 @default.
• W1938185710 cites W1988790447 @default.
• W1938185710 cites W1990517470 @default.
• W1938185710 cites W1996404651 @default.
• W1938185710 cites W1997390900 @default.
• W1938185710 cites W1999011285 @default.
• W1938185710 cites W2000780592 @default.
• W1938185710 cites W2004683093 @default.
• W1938185710 cites W2005201432 @default.
• W1938185710 cites W2009074768 @default.
• W1938185710 cites W2010348345 @default.
• W1938185710 cites W2011039300 @default.
• W1938185710 cites W2011101028 @default.
• W1938185710 cites W2018590585 @default.
• W1938185710 cites W2019363670 @default.
• W1938185710 cites W2022135397 @default.
• W1938185710 cites W2022775778 @default.
• W1938185710 cites W2027026606 @default.
• W1938185710 cites W2028631633 @default.
• W1938185710 cites W2029058452 @default.
• W1938185710 cites W2029538739 @default.
• W1938185710 cites W2029817244 @default.
• W1938185710 cites W2030012268 @default.
• W1938185710 cites W2030907583 @default.
• W1938185710 cites W2032143644 @default.
• W1938185710 cites W2033072307 @default.
• W1938185710 cites W2035742760 @default.
• W1938185710 cites W2035837996 @default.
• W1938185710 cites W2039683780 @default.
• W1938185710 cites W2042313354 @default.
• W1938185710 cites W2045313701 @default.
• W1938185710 cites W2048448061 @default.
• W1938185710 cites W2053913299 @default.
• W1938185710 cites W205486567 @default.
• W1938185710 cites W2058050990 @default.

• next