INDUCTION OVER THE UNEXPLAINED: Integrated Learning of Concepts with Both Explainable and Conventional Aspects

Mooney, Raymond J.; Ourston, Dirk

doi:10.1016/b978-1-55860-036-2.50005-9

Cited by 34 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been few attempts to combine empirical and knowledge-based learning in cognitive psychology (but see Heit, 1994; Pazzani, 1991; Wisniewski & Medin, 1991 , 1994a). However, various schemes for combining these factors have received a great deal of attention in artificial intelligence research (e.g., Flann & Dietterich, 1989; Lebowitz, 1986; Mooney, 1993; Ourston & Mooney, 1989; Ourston & Mooney, 1990; Pazzani, 1985, 1988; Pazzani, Dyer, & Flowers, 1987; Towell, Shavlik, & Noordeweir, 1990; Yoo & Fisher, 1991). In this article, I address this issue with respect to novel artifacts and their functions, drawing on some ideas from artificial intelligence.…”

mentioning

confidence: 99%

“…A number of models use integrated learning. Mooney’s (Mooney, 1993; Mooney & Ourston, 1989) Induction over the Unexplained (IOU) system performs a knowledge-based causal analysis that separates functionally relevant features from those that are functionally irrelevant. Operating along side the knowledge-based component is an empirical learning algorithm that determines which of the irrelevant features are diagnostic of category membership.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Prior knowledge and functionally relevant features in concept learning.

Wisniewski¹

1995

Journal of Experimental Psychology: Learning, Memory, and Cogni

129

108

View full text Add to dashboard Cite

Empirical learning models have typically focused on statistical aspects of features (e.g., cue and category validity). In general, these models do not address the contact between people's prior knowledge that lies outside the category and their experiences of the category. A variety of extensions to these models are examined, which combine prior knowledge with empirical learning. Predictions of these models were compared in 4 experiments. These studies contrasted the cue and category validity of features with people's prior knowledge about the relevance of features to the functions of novel artifacts. The findings suggest that the influences of knowledge and experience are more tightly integrated than some models would predict. Furthermore, relatively straightforward ways of incorporating knowledge into an empirical learning algorithm appear insufficient (e.g., use of knowledge to weight features by general relevance or to individually weight features). Other extensions to these models are suggested that focus on the importance of intermediary features, coherence, and conceptual roles.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Prior knowledge and functionally relevant features in concept learning.

Wisniewski¹

1995

Journal of Experimental Psychology: Learning, Memory, and Cogni

129

108

View full text Add to dashboard Cite

show abstract

Concepts and Categorization

Wisniewski

2002

Stevens' Handbook of Experimental Psychology

View full text Add to dashboard Cite

Traditionally, concepts have been viewed as mental representations that enable people to categorize or pick out a group of nonidentical but equivalent things (e.g., a concept of dog allows one to categorize many entities as “dogs” even though they are not identical). This chapter provides a broad overview of the fields of concepts and categorization, describing early research but giving special attention to work published in the last 15 years. It describes different views of the structure of human concepts (i.e., what they consist of), as well as formal mathematical models of categorization and category learning. These models assume that categorization is based on how similar an entity is to other members of the empirical category. This chapter describes research addressing the sufficiency of this approach, which suggests that similarity is a dynamic process involving the comparison of complex mental representations, and that category learning involves the integration of empirical learning with background knowledge. The chapter also examines research describing the taxonomic and thematic organization of concepts in memory. Finally, the chapter addresses the functions that concepts serve beyond their traditional role in classification.

show abstract

Integrating machine-learning techniques in knowledge-based systems verification

Lounis

1993

Lecture Notes in Computer Science

View full text Add to dashboard Cite

INDUCTION OVER THE UNEXPLAINED: Integrated Learning of Concepts with Both Explainable and Conventional Aspects

Cited by 34 publications

References 2 publications

Prior knowledge and functionally relevant features in concept learning.

Prior knowledge and functionally relevant features in concept learning.

Concepts and Categorization

Integrating machine-learning techniques in knowledge-based systems verification

Contact Info

Product

Resources

About