Semisupervised category learning: The impact of feedback in learning the information-integration task

Vandist, Katleen; Schryver, Maarten De; Rosseel, Yves

doi:10.3758/app.71.2.328

Cited by 20 publications

(30 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This in turn suggests that SSL may be less apparent in multi‐dimensional tasks with separable stimulus dimensions: If the interesting distributional information from unlabeled items happens to be carried by stimulus dimensions that are unattended/unselected, then this information will not be available to influence learning. Such a result was reported by Vandist, De Schryver, and Rosseel (), who failed to find evidence for SSL that employed Gabor patches varying in frequency and orientation as the feature dimensions. On the other hand, participants may be more strongly influenced by the full distribution of unlabeled items in the feature space when stimulus dimensions are integral.…”

Section: Some Challenges For Models Of Sslsupporting

confidence: 52%

Human Semi‐Supervised Learning

Gibson

Rogers

Zhu

2013

Topics in Cognitive Science

View full text Add to dashboard Cite

Most empirical work in human categorization has studied learning in either fully supervised or fully unsupervised scenarios. Most real-world learning scenarios, however, are semi-supervised: Learners receive a great deal of unlabeled information from the world, coupled with occasional experiences in which items are directly labeled by a knowledgeable source. A large body of work in machine learning has investigated how learning can exploit both labeled and unlabeled data provided to a learner. Using equivalences between models found in human categorization and machine learning research, we explain how these semi-supervised techniques can be applied to human learning. A series of experiments are described which show that semi-supervised learning models prove useful for explaining human behavior when exposed to both labeled and unlabeled data. We then discuss some machine learning models that do not have familiar human categorization counterparts. Finally, we discuss some challenges yet to be addressed in the use of semisupervised models for modeling human categorization.Keywords: Category learning; Semi-supervised learning; Machine learning Cognitive psychology has long had an interest in understanding human categorization: how we come to conceive of objects in the world as belonging to different categories, and how we use categories to draw inferences about the unobserved properties of objects. Toward this end, one of the most commonly used experimental paradigms has been supervised category learning: On each trial, the participant views a stimulus and must guess to which of a small number of categories it belongs. Feedback is provided that indicates either whether the guess was correct or what the correct answer was-the learning is supervised in this sense. The experimenter then measures how rapidly the participant learns to generate correct inferences about category membership, and how the acquired knowledge generalizes to novel stimuli.Correspondence should be sent to Bryan R. Gibson,

show abstract

Section: Some Challenges For Models Of Sslsupporting

confidence: 52%

Human Semi‐Supervised Learning

Gibson

Rogers

Zhu

2013

Topics in Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Although the conditions under which adults most successfully use SSL are still under investigation (cf. McDonnell, Jew, & Gureckis, ; Rogers, Gibson, Harrison, & Zhu, ; Vandist, De Schryver, & Rosseel, ), adults appear to readily engage in SSL, drawing on both labeled and unlabeled exemplars to learn new categories.…”

Section: Introductionmentioning

confidence: 99%

A little labeling goes a long way: Semi‐supervised learning in infancy

LaTourrette

Waxman

2018

Developmental Science

View full text Add to dashboard Cite

There is considerable evidence that labeling supports infants' object categorization. Yet in daily life, most of the category exemplars that infants encounter will remain unlabeled. Inspired by recent evidence from machine learning, we propose that infants successfully exploit this sparsely labeled input through "semi-supervised learning." Providing only a few labeled exemplars leads infants to initiate the process of categorization, after which they can integrate all subsequent exemplars, labeled or unlabeled, into their evolving category representations. Using a classic novelty preference task, we introduced 2-year-old infants (n = 96) to a novel object category, varying whether and when its exemplars were labeled. Infants were equally successful whether all exemplars were labeled (fully supervised condition) or only the first two exemplars were labeled (semi-supervised condition), but they failed when no exemplars were labeled (unsupervised condition). Furthermore, the timing of the labeling mattered: when the labeled exemplars were provided at the end, rather than the beginning, of familiarization (reversed semi-supervised condition), infants failed to learn the category. This provides the first evidence of semi-supervised learning in infancy, revealing that infants excel at learning from exactly the kind of input that they typically receive in acquiring real-world categories and their names.

show abstract

“…In conclusion, in unsupervised learning people have the tendency to use very simple categorization rules, whereas in supervised learning participants are able to learn very complex categorization structures. Vandist, De Schryver, and Rosseel (2009) argued that both supervised and unsupervised learning are ecologically rare. Translated to daily life, supervised learning means that for every object that we observe we immediately receive correct information about its category label.…”

Section: For Amentioning

confidence: 99%

“…Both types of category learning therefore do not represent our daily reality. In a previous study Vandist et al (2009) argued that people instead learn in a semisupervised way: when confronted with (new) objects (e.g., a dog), sometimes category information will be provided (Blook, a dog^) and sometimes not. This idea is supported by Gibson, Rogers, and Zhu (2013).…”

Section: For Amentioning

confidence: 99%

“…For example, a block in a 25% semisupervised classification learning paradigm consists of 25% feedback trials and 75% no-feedback trials. Vandist et al (2009) compared the effects of this semisupervised learning process to supervised and unsupervised learning processes by using the information-integration structure. This category structure is frequently used in category learning research (e.g., Ashby et al, 2002;Ashby & Ell, 2001;Ell & Ashby, 2006;Maddox, Ashby, Ing, & Pickering, 2004a;Maddox & Filoteo, 2011;Maddox & Ing, 2005;Maddox, Pacheco, Reeves, Zhu, & Schnyer, 2010b;Paul, Boomer, Smith, & Ashby, 2011;Spiering & Ashby, 2008a, b;Vermaercke, Cop, Willems, D'Hooge, & Op de Beeck, 2014).…”

Section: For Amentioning

confidence: 99%

See 1 more Smart Citation

Semisupervised category learning facilitates the development of automaticity

Vandist

Storms

Bussche

2018

Atten Percept Psychophys

Self Cite

View full text Add to dashboard Cite

In the human category of learning, learning is studied in a supervised, an unsupervised, or a semisupervised way. The rare human semisupervised category of learning studies all focus on early learning. However, the impact of the semisupervised category learning late in learning, when automaticity develops, is unknown. Therefore, in Experiment 1, all participants were first trained on the information-integration category structure for 2 days until they reached an expert level. Afterwards, half of the participants learned in a supervised way and the other half in a semisupervised way over two successive days. Both groups received an equal number of feedback trials. Finally, all participants took part in a test day where they were asked to respond as quickly as possible. Participants were significantly faster on this test in the semisupervised group than in the supervised group. This difference was not found on day 2, implying that the no-feedback trials in the semisupervised condition facilitated automaticity. Experiment 2 was designed to test whether the higher number of trials in the semisupervised condition of Experiment 1 caused the faster response times. We therefore created an almost supervised condition where participants almost always received feedback (95%) and an almost unsupervised condition where participants almost never received feedback (5%). All conditions now contained an equal number of trials to the semisupervised condition of Experiment 1. The results show that receiving feedback almost always or almost never led to slower response times than the semisupervised condition of Experiment 1. This confirms the advantage of semisupervised learning late in learning.

show abstract

Semisupervised category learning: The impact of feedback in learning the information-integration task

Cited by 20 publications

References 33 publications

Human Semi‐Supervised Learning

Human Semi‐Supervised Learning

A little labeling goes a long way: Semi‐supervised learning in infancy

Semisupervised category learning facilitates the development of automaticity

Contact Info

Product

Resources

About