Results 21 to 30 of about 1,401,134 (269)

Predicting Category Intuitiveness With the Rational Model, the Simplicity Model, and the Generalized Context Model [PDF]

open access: yes, 2009
Naïve observers typically perceive some groupings for a set of stimuli as more intuitive than others. The problem of predicting category intuitiveness has been historically considered the remit of models of unsupervised categorization.
Bailey, T. M., Pothos, E. M.
core   +1 more source

Cross-X Learning for Fine-Grained Visual Categorization [PDF]

open access: yesIEEE International Conference on Computer Vision, 2019
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
W. Luo   +7 more
semanticscholar   +1 more source

Deep Pyramid Convolutional Neural Networks for Text Categorization

open access: yesAnnual Meeting of the Association for Computational Linguistics, 2017
This paper proposes a low-complexity word-level deep convolutional neural network (CNN) architecture for text categorization that can efficiently represent long-range associations in text.
Rie Johnson, Tong Zhang
semanticscholar   +1 more source

Content-based book recommending using learning for text categorization [PDF]

open access: yesDigital library, 1999
Recommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes.
R. Mooney, Loriene Roy
semanticscholar   +1 more source

Using bag-of-concepts to improve the performance of support vector machines in text categorization [PDF]

open access: yes, 2004
This paper investigates the use of concept-based representations for text categorization. We introduce a new approach to create concept-based text representations, and apply it to a standard text categorization collection. The representations are used as
Cöster, Rickard, Sahlgren, Magnus
core   +3 more sources

A review of emotion sensing: categorization models and algorithms

open access: yesMultimedia tools and applications, 2020
Sentiment analysis consists in the identification of the sentiment polarity associated with a target object, such as a book, a movie or a phone. Sentiments reflect feelings and attitudes, while emotions provide a finer characterization of the sentiments ...
Zhaoxia Wang, Seng-Beng Ho, E. Cambria
semanticscholar   +1 more source

Similarity and categorisation: getting dissociations in perspective [PDF]

open access: yes, 2004
Dissociations between similarity and categorization have constituted critical counter-evidence to the view that categorization is similarity-based. However, there have been difficulties in replicating such dissociations.
Braisby, Nick
core   +1 more source

On the adequacy of current empirical evaluations of formal models of categorization [PDF]

open access: yes, 2012
Categorization is one of the fundamental building blocks of cognition, and the study of categorization is notable for the extent to which formal modeling has been a central and influential component of research.
Pothos, E. M., Wills, A. J.
core   +1 more source

Categorical Combinators

open access: yesInformation and Control, 1986
The paper presents a connection between lambda-calculus and Cartesian closed categories in an untyped and purely syntactic setting. Syntactic equivalence is established between lambda-calculus with products and projections as independent operations (yielding surjective pairing besides ordinary \(\beta\)- and \(\eta\)-rules), and ''categorical ...
openaire   +1 more source

Categorical results do not imply categorical perception [PDF]

open access: yesPerception & Psychophysics, 1982
Categorical perception refers to the ability to discriminate between- but not within-category differences along a stimulus continuum. Although categorical perception was thought to be unique to speech, recent studies have yielded similar results with nonspeech continua.
J M, Hary, D W, Massaro
openaire   +2 more sources

Home - About - Disclaimer - Privacy