EURISKO: A Program That Learns New Heuristics and Domain Concepts

By D. Lenat. 1983

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

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch (2020, background): “Early approaches have proposed to search for programs that improve themselves (Lenat, 1983; Schmidhuber, 1987).”
Never-Ending Learning (2015, background): “Lenat’s work on AM and Eurisko (Lenat 1983) represents an attempt to build a system that invents concepts, then uses these as primitives for inventing more complex concepts, but again this system was never allowed to run for a sustained period, because the author determined it would quickly reach a ”
Why AM and Eurisko Appear to Work (1983, background): “Since 1977, Lenat has worked on building and extending the EURISKO program, the descendant of AM, see [10, 11, 12 ].”
Utility function security in artificially intelligent agents (2014, background): “In fact, both historical examples given below come from a single system (Eurisko) developed in the late 1970s by Lenat (1983).”
Toward an Architecture for Never-Ending Language Learning (2010, unknown): “AI has a long history of research on autonomous agents, problem solving, and learning, e.g., SOAR (Laird, Newell, and Rosenbloom 1987), PRODIGY (Carbonell et al. 1991), EURISKO (Lenat 1983), ACT-R (Anderson et al. 2004), and ICARUS (Langley et al. 1991).”
Theory Formation by Heuristic Search (1983, methodology): “The EURISKO program was built embodying this expanded model, and the reader is referred to [ 21 ] for details of its architecture, results, and our conchtsions from ten thousand hours' experience running that program.”