Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Similarity and Analogical Reasoning
19891.6k citationsStella Vosniadou, Stella Vosniadou et al.Cambridge University Press eBooksprofile →
Author Peers
Peers are selected by citation overlap in the author's most active subfields.
citations ·
hero ref
This map shows the geographic impact of Gerald DeJong's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Gerald DeJong with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Gerald DeJong more than expected).
This network shows the impact of papers produced by Gerald DeJong. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Gerald DeJong. The network helps show where Gerald DeJong may publish in the future.
Co-authorship network of co-authors of Gerald DeJong
This figure shows the co-authorship network connecting the top 25 collaborators of Gerald DeJong.
A scholar is included among the top collaborators of Gerald DeJong based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Gerald DeJong. Gerald DeJong is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Kuter, Ugur, et al.. (2007). Learning constraints via demonstration for safe planning. National Conference on Artificial Intelligence. 12–17.3 indexed citations
2.
DeJong, Gerald, et al.. (2003). The influence of reward on the speed of reinforcement learning: an analysis of shaping. International Conference on Machine Learning. 440–447.28 indexed citations
3.
DeJong, Gerald, et al.. (2002). Reinforcement Learning and Shaping: Encouraging Intended Behaviors. International Conference on Machine Learning. 355–362.11 indexed citations
4.
Brodie, Mark S. & Gerald DeJong. (1999). Learning to Ride a Bicycle using Iterated Phantom Induction. International Conference on Machine Learning. 57–66.1 indexed citations
5.
Gratch, Jonathan, Steve Chien, & Gerald DeJong. (1994). Improving learning performance through rational resource allocation. National Conference on Artificial Intelligence. 576–581.8 indexed citations
6.
Chien, Steve & Gerald DeJong. (1994). Constructing simplified plans via Truth Criteria approximation. 19–24.10 indexed citations
7.
DeJong, Gerald & Scott Bennett. (1993). Permissive planning: a machine learning approach to linking internal and external worlds. National Conference on Artificial Intelligence. 508–513.3 indexed citations
8.
Gratch, Jonathan & Gerald DeJong. (1992). COMPOSER: a probabilistic solution to the utility problem in speed-up learning. National Conference on Artificial Intelligence. 235–240.47 indexed citations
9.
Chien, Steve, Melinda Gervasio, & Gerald DeJong. (1992). Learning to integrate reactivity and deliberation in uncertain planning and scheduling problems. National Conference on Artificial Intelligence.1 indexed citations
10.
Vosniadou, Stella, Stella Vosniadou, Stella Vosniadou, et al.. (1989). Similarity and Analogical Reasoning. Cambridge University Press eBooks.1600 indexed citations breakdown →
11.
DeJong, Gerald. (1988). Some thoughts on the present and future of explanation-based learning. European Conference on Artificial Intelligence. 690–697.4 indexed citations
12.
DeJong, Gerald, et al.. (1987). The classification, detection and handling of imperfect theory problems. Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign). 205–207.26 indexed citations
13.
Shavlik, Jude & Gerald DeJong. (1987). An explanation-based approach to generalizing number. Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign). 236–238.14 indexed citations
14.
Mooney, Raymond J. & Gerald DeJong. (1985). Learning schemata for natural language processing. International Joint Conference on Artificial Intelligence. 681–687.60 indexed citations
15.
DeJong, Gerald, et al.. (1985). Towards a model of conceptual knowledge acquisition through directed experimentation. International Joint Conference on Artificial Intelligence. 688–690.13 indexed citations
16.
DeJong, Gerald. (1983). Acquiring schemata through understanding and generalizing plans. International Joint Conference on Artificial Intelligence. 462–464.31 indexed citations
17.
DeJong, Gerald. (1982). Automatic schema acquisition in a natural language environment. National Conference on Artificial Intelligence. 410–413.8 indexed citations
18.
DeJong, Gerald. (1981). Generalizations based on explanations. International Joint Conference on Artificial Intelligence. 67–69.48 indexed citations
19.
Schank, Roger C., Janet L. Kolodner, & Gerald DeJong. (1980). Conceptual information retrieval. International ACM SIGIR Conference on Research and Development in Information Retrieval. 94–116.34 indexed citations
20.
DeJong, Gerald. (1977). Skimming newspaper stories by computer. Defense Technical Information Center (DTIC). 16–16.17 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.