An integrated framework for empirical discovery

Nordhausen, Bernd; Langley, Pat

doi:10.1007/bf00993059

Cited by 27 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generality, accuracy and utility of laws (theorems and models) justify the investment made by introduction of a concept used in those laws (theorems, models). Automated scientific discovery systems (BACON: Langley et al 1987; IDS: Nordhausen & Langley, 1993;FAHRENHEIT: Zytkow, 1996) explore this view of concepts, keeping them only when justified by the simultaneously discovered knowledge.…”

Section: Concepts and Knowledgementioning

confidence: 98%

<title>Granularity refined by knowledge: contingency tables and rough sets as tools of discovery</title>

Żytkow

2000

SPIE Proceedings

View full text Add to dashboard Cite

Contingency tables represent data in a granular way and are a well-established tool for inductive generalization of knowledge from data. We show that the basic concepts of rough sets, such as concept approximation, indiscernibility, and reduct can be expressed in the language of contingency tables. We further demonstrate the relevance to rough sets theory of additional probabilistic information available in contingency tables and in particular of statistical tests of significance and predictive strength applied to contingency tables. Tests of both type can help the evaluation mechanisms used in inductive generalization based on rough sets. Granularity of attributes can be improved in feedback with knowledge discovered in data. We demonstrate how 49er's facilities for (1) contingency table refinement, for (2) column and row grouping based on correspondence analysis, and (3) the search for equivalence relations between attributes improve both granularization of attributes and the quality of knowledge. Finally we demonstrate the limitations of knowledge viewed as concept approximation, which is the focus of rough sets. Transcending that focus and reorienting towards the predictive knowledge and towards the related distinction between possible and impossible (or statistically improbable) situations will be very useful in expanding the rough sets approach to more expressive forms of knowledge.

show abstract

Section: Concepts and Knowledgementioning

confidence: 98%

<title>Granularity refined by knowledge: contingency tables and rough sets as tools of discovery</title>

Żytkow

2000

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Soon afterwards, based on inductive learning and logical reasoning, a number of systems, such as STAHL [60], FAH-RENHEIT [61] and IDS [38], were developed in this field. In China, Chinese scholars, such as Wu [52], have made fruitful achievements in mechanical theorem proving in geometries.…”

Section: Technical Originsmentioning

confidence: 99%

“…In order to build a solid theory foundation for the future development of UKD, the concept of UKD is defined, and various categories of universal knowledge are described. To accelerate the development of UKD, a unified research paradigm should be built based on techniques and paradigms from related research domains, which include not only data mining, but also machine discovery [28,29,38,52,60,61], big data analytics [16,31,43,56,58,59] and complex systems science [8,22,41,42,51,53]. To meet this need, a novel research paradigm called dual-cycle methodology is proposed.…”

Section: Introductionmentioning

confidence: 99%

Universal knowledge discovery from big data using combined dual-cycle

Shen

2015

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Many people hold a vision that big data will provide big insights and have a big impact in the future. However, how to turn big data into deep insights with tremendous value still remains obscure. Here I highlight universal knowledge discovery from big data. The new concept focuses on discovering universal knowledge, which exists in the statistical analyses of big data and provides valuable insights into big data. Universal knowledge comes in different forms, e.g., universal patterns, rules, correlations, models and mechanisms. To accelerate big data assisted scientific discovery, a unified research paradigm should be built based on techniques and paradigms from related research domains, especially big data mining and complex systems science. Therefore, I propose a dual-cycle methodology with three types of cycle-driven UKD process, i.e., big-data-cycle-driven, mechanism-cycle-driven and combined-dual-cycle-driven mining. A case study is also given to illustrate the effectiveness of the proposed processes. This paper lays a foundation for the future development of universal knowledge discovery, and offers a pathway to the discovery of ''treasure-trove'' hidden in big data.

show abstract

“…For instance, Nordhausen & Pazzani (1993) proposes a method to learn causal relation from observations, and Saitta and co-workers developed the system WHY, which exploits a causal model to learn and revise a set of rules [Saitta, Botta, & Neri, 1993;Baroglio, Botta, & Saitta, 1994]. More oriented to the development of tutoring systems, Sleeman et al (1990) present a model of a student learning high-school algebra.…”

Section: Artificial Intelligencementioning

confidence: 99%

Untitled

Neri

2000

Machine Learning

View full text Add to dashboard Cite

Abstract. The goal of the reported research is the development of a computational approach that could help a cognitive scientist to interactively represent a learner's mental models, and to automatically validate their coherence with respect to the available experimental data. In a reported case-study, the student's mental models are inferred from questionnaires and interviews collected during a sequence of teaching sessions. These putative cognitive models are based on a theory of knowledge representation, derived from psychological results and educational studies, which accounts for the evolution of the student's knowledge over a learning period. The learning system WHY, able to handle (causal) domain knowledge, shows how to model the answers and the causal explanations given by the learner.

show abstract

An integrated framework for empirical discovery

Cited by 27 publications

References 19 publications

<title>Granularity refined by knowledge: contingency tables and rough sets as tools of discovery</title>

<title>Granularity refined by knowledge: contingency tables and rough sets as tools of discovery</title>

Universal knowledge discovery from big data using combined dual-cycle

Untitled

Contact Info

Product

Resources

About