Learning structural descriptions from examples

By Patrick Henry Winston. 1970

Subfields: Representation & Self-Supervised Learning, Statistical Learning Theory

How researchers see this paper

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

In Representation & Self-Supervised Learning

In Statistical Learning Theory

Citations in the corpus

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning (2020, methodology): “It is worth noting that similar setups were proposed previously in a less realistic setting as in (Janner et al., 2018; Bapst et al., 2019; McCarthy et al.; Akkaya et al., 2019; Fahlman, 1974; Winston, 1970; Winograd, 1972).”
Structured agents for physical construction (2019, background): “Early work explored physical concepts with an emphasis on descriptions that generalize across diverse settings (Winston, 1970).”
Visual Interaction Networks: Learning a Physics Simulator from Video (2017, background): “Physical reasoning is a core domain of human knowledge [22] and among the earliest topics in AI [24, 25].”
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning (2018, background): “Despite being a core focus of the earliest days of artiﬁcial intelligence and computer vision research (Roberts, 1963; Winston, 1970), a similar level of physical scene understanding remains elusive for machines.”
Theory Formation by Heuristic Search (1983, background): “Again, simple models exist and lead to concise, effective computer programs for this kind of inductive task [6, 38 ].”
A framework for representing knowledge (1974, methodology): “The different frames of a system resemble the multiple "models" described in Guzman (1967) and Winston (1970).”
Recognition-by-components: a theory of human image understanding. (1987, background): “The representation of an object would thus be a structural description that expressed the relations among the components (Ballard & Brown, 1982; Winston, 1975).”
Description and Recognition of Curved Objects (1977, methodology): “Techniques similar to those presented by Winston in [ 15 ] are applicable, however, incomplete and imperfect descriptions must be reckoned with.”
On the computational architecture of the neocortex (2004, methodology): “A key idea in early AI work on speech perception (the CMU work on HEARSAY, cf. Erman et al. 1980) as well as the psychological model embodied in 'Pandemonium' (see Selfridge 1959 or Lindsey and Norman 1977, p. 259 ), is that of the blackboard.”
Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework (1988, background): “In [15] one extension to structured instance spaces (e.g. the blocks world [ 45 ]) is given.”
Learning and reasoning by analogy (1980, background): “The first of these is known as the ARCH system [20], and the second, FOX [21], both being identified by the typical things involved in the learning.”
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning (2021, methodology): “The AI community has been using the “blocks world” for decades as a testbed for various AI problems, including learning theory [Winston, 1970], natural language [Winograd, 1972], and planning [Fahlman, 1974].”
Induction of Decision Trees (1986, background): “A quite different approach sees learning as the acquisition of structured knowledge in the form of concepts (Hunt, 1962; Winston, 1975), -discrimination nets (Feigenbaum and Simon, 1963), or production rules (Buchanan, 1978).”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “ures should be described in terms of functions provided and functions performed. The concept of affordance was later coined by Gibson [243]. Based on the classic geometrybased “arch-learning” program [261], Winston et al. [262] discussed the use of function-based descriptions of object categories. T”