Object name Learning Provides On-the-Job Training for Attention

By Linda B. Smith, S. Jones, Barbara Landau, Lisa Gershkoff-Stowe, Larissa K. Samuelson. 2002

576 citations recorded by the source corpus.

Subfields: Automotive Engineering, Developmental and Educational Psychology

How researchers see this paper

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

In Automotive Engineering

In Developmental and Educational Psychology

Citations in the corpus

Learning with Hierarchical-Deep Models (2013, background): “…learns to learn novel concepts from very few training example by learning low-level generic features, high-level features that capture correlations among low-level features, and a category hierarchy for sharing priors over the high-level features that are typical of different kinds of concepts.”
Frustratingly Simple Few-Shot Object Detection (2020, background): “Even a toddler can easily recognize a new concept with very little instruction (Landau et al., 1988; Samuelson & Smith, 2005; Smith et al., 2002).”
Word learning and the acquisition of syntactic-semantic overhypotheses (2018, unknown): “The shape bias (Smith et al., 2002; Kemp et al., 2007) is one of the strongest examples of an overhypothesis in language learning, according to which children reliably generalize labels for object categories based on the shape of their referents.”
A Developmental Approach to Machine Learning? (2017, background): “…object categories in the context of object play causes an earlier than typical emergence of the shape bias in 1 1 / 2 -year-olds, and an early increase in the rate of growth of these children’s vocabularies (Samuelson, 2002; Smith et al., 2002; Yoshida and Smith, 2005; Perry et al., 2010).”
Learning to Learn with Compound HD Models (2011, background): “For humans learners, however, just one or a few examples are often sufﬁcient to grasp a new category and make meaningful generalizations to novel instances [25, 16].”
The Omniglot Challenge: A 3-Year Progress Report (2019, background): “Even with considerable augmentation, this is still substantially higher than BPL, which like children can learn to learn from quite limited amounts of background experience (Smith et al., 2002), perhaps familiarity with only one or a few alphabets along with related drawing experience.”
A probabilistic account of exemplar and category generation. (2013, background): “One developmental study suggests that children learn to expect exemplars of an object category to be similar in shape, even if they vary along other dimensions such as color and texture (Smith et al., 2002).”
Predicting the birth of a spoken word (2015, background): “Many factors contribute to word learning, ranging from social information about speakers’ intentions (3, 4) to biases that lead children to extend categories appropriately (5, 6).”