A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Statistical Learning of Higher-Order Spatial Structures from Visual Scenes
2001
Psychological Science
Preserved Fulltext
•The process of learning the co-occurrences between objects has been linked to higher order representations in the visual cortex (Logothetis & Sheinberg 1996) . ...
•There is no direct evidence of visual statistical learning on eye movement changes. ...
doi:10.1111/1467-9280.00392
pmid:11760138
fatcat:iiil7lhnn5hkpdhfylbwd5zqiq
Multi-Task Learning with High-Order Statistics for X-vector based Text-Independent Speaker Verification
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
- and higher-order statistics of the original input utterance. ...
The proposed training strategy aggregates both the supervised and unsupervised learning into one framework to make the speaker embeddings more discriminative and robust. ...
Multi-task learning with high-order statistics
High-order statistics Higher-order statistics can be used in estimation of the shape of unimodal distributions and have been applied to many tasks [14, ...
arXiv:1903.12058v2
fatcat:dlreitygybhtrhnjtpyotdjp2m
Multi-Task Learning with High-Order Statistics for x-Vector Based Text-Independent Speaker Verification
2019
Interspeech 2019
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
higher-order statistics of the original input utterance. ...
The proposed training strategy aggregates both the supervised and unsupervised learning into one framework to make the speaker embeddings more discriminative and robust. ...
High-order statistics Higher-order statistics can be used in estimation of the shape of unimodal distributions and have been applied to many tasks [14, 15, 16] . ...
doi:10.21437/interspeech.2019-2264
dblp:conf/interspeech/YouGDD19
fatcat:h3igss5kf5dkxbjnj5hleiq42i
Learning multiview face subspaces and facial pose estimation using independent component analysis
2005
IEEE Transactions on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
of multiview examples and the learning is done in an unsupervised way with view-unlabeled data. ...
ICA, its variants, namely independent subspace analysis (ISA) and topographic independent component analysis (TICA), take into account higher order statistics needed for object view characterization. ...
Such variations are related to higher order statistics. ...
doi:10.1109/tip.2005.847295
pmid:15971770
fatcat:w7qbp76dcne3ne6m232a3a5r3u
HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we explore the benefits of using higher-order statistics (mainly refer to third-order and fourth-order statistics) for domain matching. ...
Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. ...
Higher-order Statistics The statistics higher than firstorder has been success fully used in many classical and deep learning methods [9, 19, 30, 22, 12] . ...
arXiv:1912.11976v1
fatcat:aa5k34pqgrhxrazxzutpxkytvm
HoMM: Higher-Order Moment Matching for Unsupervised Domain Adaptation
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Moreover, HoMM (order≥ 3) is expected to perform fine-grained domain alignment as higher-order statistics can approximate more complex, non-Gaussian distributions. ...
Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. ...
Higher-order Statistics The statistics higher than first-order has been successfully used in many classical and deep learn-ing methods (De Lathauwer, Castaing, and Cardoso 2007; Koniusz et al. 2016; Gou ...
doi:10.1609/aaai.v34i04.5745
fatcat:geowmlfwjrgtdklzqzu3lsbhjm
Generating adaptive and robust filter sets using an unsupervised learning framework
2017
2017 IEEE International Conference on Image Processing (ICIP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1811.08927v1 fatcat:jjlsgjji25cxbd7knyuqgswcia
In this paper, we introduce an adaptive unsupervised learning framework, which utilizes natural images to train filter sets. ...
Based on experiments, we show that the filter responses span a set in which a monotonicity-based metric can measure both the perceptual dissimilarity of natural images and the similarity of texture images ...
ZCA whitening is a decorrelating procedure that removes the first and the second order statistics of input data and forces the ensuing learning stage to capture higher order statistics. ...
doi:10.1109/icip.2017.8296841
dblp:conf/icip/PrabhushankarTA17
fatcat:4yw775ikqnf2recsbgikurxdta
Unsupervised Learning of P NP P Word Combinations
[chapter]
2005
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
We evaluate the possibility to learn, in an unsupervised manner, a list of idiomatic word combinations of the type preposition + noun phrase + preposition (P NP P), namely, such groups with three or more ...
simple forms that behave as a whole lexical unit and have semantic and syntactic properties not deducible from the corresponding properties of each simple form, e.g., by means of, in order to, in front ...
Unsupervised Learning of P NP P Word Combinations. ...
doi:10.1007/978-3-540-30586-6_37
fatcat:zxaiekakzbfjzgkn5imogvgmj4
Student Behavior and Performance in Unsupervised Online Quizzes: A Case of Computer Organization Course
2019
International Journal of Advanced Trends in Computer Science and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Unsupervised online quizzes have been used widely by higher learning institutions as an activity in a blended learning model and found to be a valuable formative assessment tool for students to self-assess ...
The results of the study suggested that students who frequently access to printed references, access to digital references, and have peer discussion during online quiz taking obtained higher marks for ...
RESULTS AND DISCUSSIONS The data of the study were analyzed using IBM SPSS Statistics Version 25. ...
doi:10.30534/ijatcse/2019/69852019
fatcat:mwb2tbivzjdhrfs4qidgupz35e
Unsupervised Texture Classification And Segmentation
2007
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
When applied to textures, the algorithm can learn basis functions for images that capture the statistically significant structure intrinsic in the images. ...
We apply this technique to the problem of unsupervised texture classification and segmentation. ...
Each class is learned in an unsupervised fashion and contains the statistical intrinsic structure of its image texture. ...
doi:10.5281/zenodo.1332180
fatcat:gx6hru6j7bbejeferxj4aqpame
Independent Component Analysis
[chapter]
2009
Encyclopedia of Biometrics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
PCA Linear transform Compression (dimensionality reduction) Classification (feature extraction) PCA Second-order statistics (Gaussian) Linear orthogonal transform Optimal coding in MS sense ICA Higher-order ...
Theorem The steepest descent direction of J (w) in a Riemannian space is given by / 78 Theory and Preliminaries for ICA Algorithms for ICA Beyond ICA Applications of ICA Criteria Unsupervised Learning ...
Theory and Preliminaries for ICA
Algorithms for ICA
Beyond ICA
Applications of ICA
Criteria
Unsupervised Learning Algorithms
Algebraic Algorithms
More Algebraic Algorithms
FOBI: 4th-order moment ...
doi:10.1007/978-0-387-73003-5_305
fatcat:odqmmnym6zddpfvggdues6fsie
NetDP: An Industrial-Scale Distributed Network Representation Framework for Default Prediction in Ant Credit Pay
2018
2018 IEEE International Conference on Big Data (Big Data)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2004.00201v1 fatcat:y6em2d36fvhhnfiu7jpnsgpfnq
Different from the manual review for credit card application in conventional banks, the credit limit of Ant Credit Pay is automatically offered to users based on the knowledge learned from big data. ...
Similar to credit card, loan default is one of the major risks of this credit product. ...
The higher value of KS statistic means the better performance.
B. Experimental Results As shows in Figure 3 (a), BenchDP outperforms NetDP. ...
doi:10.1109/bigdata.2018.8622169
dblp:conf/bigdataconf/LinZZLFFYQ18
fatcat:jn6klcbb5veanjmrahhziyxlb4
Diagnostic Value of SonoVue Contrast-Enhanced Ultrasonography in Nipple Discharge Based on Artificial Intelligence
2021
Journal of Healthcare Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper aims to explore the application value of SonoVue contrast-enhanced ultrasonography based on deep unsupervised learning (DNS) in the diagnosis of nipple discharge. ...
In this paper, a new model (ODNS) is proposed based on the unsupervised learning model and stack self-coding network. ...
compared, as shown in Figure 7 . e maximum Acc value of unsupervised deep learning model is 96.67 ± 0.45%, which is significantly higher than 91.52 ± 0.57%, 92.08 ± 0.33%, and 94.35 ± 0.64% of perceptron ...
doi:10.1155/2021/2961697
pmid:34956565
pmcid:PMC8702308
fatcat:gxqwvd5rnvdobm5ck4ghym6rxe
High-order Connectomic Manifold Learning for Autistic Brain State Identification
[chapter]
2017
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We benchmark our ASD identification method against supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high-and low-order relationships between morphological regions ...
and high-order levels. ...
High-order Connectomic Manifold Learning for Unsupervised Clustering of Autistic and Healthy BrainsIn this section, we present the high-order connectomic manifold learning for ASD identification using ...
doi:10.1007/978-3-319-67159-8_7
fatcat:cjpcvux3l5bjvpg5hqgonjkcvy
Rethinking Sampling Strategies for Unsupervised Person Re-identification
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Group sampling regulates the representation learning process, which enhances statistical stability for feature representation in a progressive fashion. ...
Unsupervised person re-identification (re-ID) remains a challenging task. ...
Unsupervised Person re-ID Unsupervised person re-ID aims to learn effective features for unlabeled person image datasets. ...
arXiv:2107.03024v2
fatcat:ft536gktn5ci7gep6zmq7jvkgm
« Previous
Showing results 1 — 15 out of 86,966 results