Learning and reasoning by analogy

By Patrick Henry Winston. 1980

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Analogical Mapping by Constraint Satisfaction (1989, background): “…is to assimilate semantic similarity to structural consistency by imposing an added restriction on the latter constraint: corresponding relations must either be identical (Falkenhainer et al., 1986)' or share common features, such as a common superordinate (Burstein, 1986; Winston, 1980).”
Schema Acquisition from One Example: Psychological Evidence for Explanation-Based Learning. (1987, background): “Similarity-based learning (Michalski, 1983; Mitchell, 1978; Quinlan, 1986) requires many examples and systems based on analogy (Carbonell. 1983; Falkenhainer, Forbus. & Gentner, 1986; Winston, 1980) require two examples, while EBL requires only a single example.”
The Structure-Mapping Engine: Algorithm and Examples (1989, unknown): “For more information, please contact forbus@ils.nwu.edu”
A Survey on In-context Learning (2022, background): “Second, in-context learning is similar to the decision process of human beings by learning from analogy (Winston, 1980).”
The Process of Schema Emergence: Assimilation, Deconstruction, Unitization and the Plurality of Analogies (2013, background): “Experimental evidence (Gick & Holyoak, 1983; Novick & Holyoak, 1991; Schustack & Anderson, 1979) and computational analysis (Winston,1980) suggest a strong relationship between the processing of concrete analogs and the formation of a general schema (e.g., learning the general concept of “pump” by…”
Structure mapping in analogy and similarity. (1997, methodology): “Here, odors and heat are used as "near-misses" (Winston, 1980)-potential analogs that differ with respect to the key behavior and serve to sharpen the parallel between light and the motive power.”
The rise and potential of large language model based agents: a survey (2025, unknown): “The key idea of ICL is learning from analogy, akin to the learning process of humans [187].”
Transfer Learning by Structural Analogy (2011, methodology): “Using analogy in problem solving, (Carbonell 1981; Winston 1980) pointed out that analogical reasoning implies that the relationship between entities must be compared, not just the entity themselves, to allow effective recall of previous experiences.”
Image Analogies (2001, background): “For this reason, a goal from the early days of artiﬁcial intelligence has been to build systems able to reason by analogy; early works include Evan’s ANALOGY program [15] and Winston’s seminal work on ﬁnding and exploiting parallels in simple theories [52].”
Computational models of analogy. (2011, background): “One promising future direction is the use of analogical models to capture learning processes in cognitive development (e.g., Refs 13,61,76,77).”