Results 261 to 270 of about 356,686 (298)

Unsupervised Learning

Neural Computation, 1989
What use can the brain make of the massive flow of sensory information that occurs without any associated rewards or punishments? This question is reviewed in the light of connectionist models of unsupervised learning and some older ideas, namely the cognitive maps and working models of Tolman and Craik, and the idea that redundancy is important for ...
openaire   +2 more sources

Adherence to Unsupervised Exercise

The Physician and Sportsmedicine, 1983
In brief: Forty-seven male police officers (mean age 41.0 years) were randomly assigned to three exercise groups: unsupervised, supervised, and control. Training consisted of walking and jogging three days per week for 20 weeks. The attrition rate for the unsupervised group (35%) was lower than for the supervised group (45%).
L R, Gettman, M L, Pollock, A, Ward
openaire   +2 more sources

Unsupervised pronunciation validation

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009
This paper addresses selecting between candidate pronunciations for out-of-vocabulary words in speech processing tasks. We introduce a simple, unsupervised method that outperforms the conventional supervised method of forced alignment with a reference. The success of this method is independently demonstrated using three metrics from large-scale speech ...
Christopher M. White, Abhinav Sethy, Bhuvana Ramabhadran, Patrick J. Wolfe, Erica Cooper, Murat Saraclar, James K. Baker   +6 more
openaire   +2 more sources

Unsupervised Learning: Clustering

2019
In this article an introduction on unsupervised cluster analysis is provided. Clustering is the organisation of unlabelled data into similarity groups called clusters. A cluster is a collection of data items which are similar between them, and dissimilar to data items in other clusters.
Serra A., Tagliaferri R.
openaire   +1 more source

Spicules for Unsupervised Learning

2009
We present a new model of unsupervised competitive neural network, based on spicules. This model is capable of detecting topological information of an input space, determining its orientation and, in most case, its skeleton.
José Antonio Gómez-Ruiz, José Muñoz-Pérez, M. Angeles García-Bernal   +2 more
openaire   +2 more sources

Unsupervised possibilistic clustering

Pattern Recognition, 2006
In fuzzy clustering, the fuzzy c-means (FCM) clustering algorithm is the best known and used method. Since the FCM memberships do not always explain the degrees of belonging for the data well, Krishnapuram and Keller proposed a possibilistic approach to clustering to correct this weakness of FCM.
Miin-Shen Yang, Kuo-Lung Wu
openaire   +2 more sources

Multilingual Unsupervised Dependency Parsing with Unsupervised POS Tags

2015
In this paper, we present experiments with unsupervised dependency parser without using any part-of-speech tags learned from manually annotated data. We use only unsupervised word-classes and therefore propose fully unsupervised approach of sentence structure induction from a raw text.
openaire   +2 more sources

Unsupervised image segmentation

Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181), 2002
We present an unsupervised segmentation algorithm comprising an annealing process to select the maximum a posteriori (MAP) realization of a hierarchical Markov random field (MRF) model. The algorithm consists of a sampling framework which unifies the processes of model selection, parameter estimation and image segmentation, in a single Markov chain. To
Simon A. Barker, Peter J. W. Rayner
openaire   +1 more source

Unsupervised coding with lococode

1997
Traditional approaches to sensory coding use code component-oriented objective functions (COCOFs) to evaluate code quality. Previous COCOFs do not take into account the information-theoretic complexity of the code-generating mapping itself. We do: “Low-complexity coding and decoding” (LOCOCODE) generates so-called lococodes that (1) convey information ...
Sepp Hochreiter, Jürgen Schmidhuber
openaire   +1 more source

On competitive unsupervised clustering

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2002
We focus on the problem of unsupervised clustering which allows automatic setting of optimal clusters number. We present a generalization of the competitive agglomeration clustering algorithm first introduced by Frigui et al. (1997). This generalization is inspired by the regularization theory and suggests a new schema for using various cluster ...
openaire   +1 more source