The formation of learning sets.

By H. Harlow. 1949

Subfields: Cognitive Science & Psychology

How researchers see this paper

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

In Cognitive Science & Psychology

Citations in the corpus

Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions (2017, background): “Learning to learn or meta-learning has been studied in cognitive science and machine learning for decades (Harlow, 1949; Thrun & Pratt, 1998; Hochreiter et al., 2001).”
Meta Networks (2017, background): “These abilities are mostly explained by the meta learning (i.e. learning to learn) process in the brain (Harlow, 1949).”
Learning to Learn for Global Optimization of Black Box Functions (2016, background): “In psychology, learning to learn has a long history full of insights on cognition [Ward, 1937, Harlow, 1949, Kehoe, 1988].”
Sample Efficient Adaptive Text-to-Speech (2018, background): “Meta-learning has a long history (Harlow, 1949; Thrun and Pratt, 2012), and recent studies include efforts to learn optimization processes (Andrychowicz et al., 2016; Chen et al., 2017) that have been shown to extend naturally to the few-shot setting (Ravi and Larochelle, 2016).”
Learned Optimizers that Scale and Generalize (2017, background): “Learning to learn has a long history in psychology (Ward, 1937; Harlow, 1949; Kehoe, 1988; Lake et al., 2016).”
Meta-Learning in Neural Networks: A Survey (2020, background): “This ‘learning-to-learn’ [7] can lead to a variety of benefits such as improved data and compute efficiency, and it is better aligned with human and animal learning [8], where learning strategies improve both on a lifetime and evolutionary timescales [8], [9], [10].”
Task-Embedded Control Networks for Few-Shot Imitation Learning (2018, background): “Humans and animals are capable of learning new information rapidly from very few examples, and apparently improve their ability to ‘learn how to learn’ throughout their lives [1].”
Neuronal Reward and Decision Signals: From Theories to Data. (2015, background): “Repeated learning of new stimuli leads to learning set performance in which animals acquire novel stimuli within a few trials (202), thus allowing to record from single neurons A”
The Microfoundations Movement in Strategy and Organization Theory (2015, background): “Specifically, the oldest citations in Cohen and Levinthal’s influential article are to behavioral psychology and learning theory related to individual knowledge acquisition based on experience, stimulus, and repetition (e.g. Bower & Hilgard, 1981; Ellis, 1965; Estes, 1970; Harlow, 1949).”
How Career Variety Promotes the Adaptability of Managers: A Theoretical Model. (2006, background): “Learning-set theory points out the importance of practicing suYcient number of related problems before a particular problem is reliably learned (Harlow, 1949, 1959).”
Motor Task Variation Induces Structural Learning (2009, unknown): “For example, cognitive ‘‘learning to learn’’ phenomena, in which subjects show facilitation in categorization or concept learning tasks if they have had random exposure to other items of a given category [ 33 ], can be recast as structural-learning phenomena.”
Learning by Doing Something Else: Variation, Relatedness, and the Learning Curve (2003, background): “Psychologists discovered learning curves in their study of individual learning processes in both humans and other species, and demonstrated the persistence of the learning curve across many different types of tasks (e.g., Harlow 1949, Thorndike 1898).”
Darwin's mistake: Explaining the discontinuity between human and nonhuman minds (2008, unknown): “(Wallace 1889, p. 478) Darwin's continuity has inspired discoveries based on fresh lines of investigation in field and in laboratory (Boesch 1991; Goodall 1986; Harlow 1949; Koehler 1925/1959; Russon & Galdikas 1993; Watanabe 1994, to name only a few).”