Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Mehran Safayani"'
Publikováno v:
هوش محاسباتی در مهندسی برق, Vol 14, Iss 1, Pp 123-134 (2023)
Anomaly detection has been in researchers’ scope of study for a long time. The wide variety of anomaly detection use cases ranges from quality control in production lines to providing security in public places. One of the most attractive topics in
Externí odkaz:
https://doaj.org/article/e7a91713cdbd4031a938e2a8f0b9386e
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2011 (2011)
Externí odkaz:
https://doaj.org/article/cbb0ab00c50b43daadbd6d10760b5e7b
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2009 (2009)
Automatic speech recognition performance degrades significantly when speech is affected by environmental noise. Nowadays, the major challenge is to achieve good robustness in adverse noisy conditions so that automatic speech recognizers can be used i
Externí odkaz:
https://doaj.org/article/beb0393235bc4d54bc516e99ee85a53e
Publikováno v:
Neurocomputing. 461:479-493
Recently, listwise collaborative filtering (CF) algorithms are attracting increasing interest due to their efficiency and prediction quality. Different from rating-oriented (pointwise) CF, they recommend a preference ranking of items to each user wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a37bbd0ecc66ca5d613ea1c357a548a
https://doi.org/10.1016/j.neucom.2021.08.076
https://doi.org/10.1016/j.neucom.2021.08.076
Publikováno v:
IEEE Transactions on Fuzzy Systems. 29:1133-1142
Restricted Boltzmann machine (RBM) is an energy-based artificial neural network (ANN), applied in several applications like image processing, topic modeling, classification, regression, and pattern recognition. The fuzzy version of RBM is a new appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f26e7e557cadba72ee3447088f67c8f2
https://doi.org/10.1109/tfuzz.2020.2969120
https://doi.org/10.1109/tfuzz.2020.2969120
Publikováno v:
The Visual Computer. 37:119-131
With the advent of deep learning, multi-modal data have been of great interest. One of the multi-modal tasks which can be included in the computer vision domain is visual question answering (VQA). In VQA, a question and an image are entered into the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1ba425f591275f1f545f3cf6a682bd3
https://doi.org/10.1007/s00371-019-01786-4
https://doi.org/10.1007/s00371-019-01786-4
Publikováno v:
IEEE Transactions on Fuzzy Systems. 26:3534-3544
In this paper, a new unsupervised metric learning algorithm with real-world application in clustering is proposed. To have a desirable clustering, the separability among different classes of data needs to be improved. A common manner in accomplishing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec6cfc7086857106264aff583618b9ce
https://doi.org/10.1109/tfuzz.2018.2836338
https://doi.org/10.1109/tfuzz.2018.2836338
Publikováno v:
Neurocomputing. 319:21-33
A great number of machine learning algorithms strongly depend on the underlying distance metric for representing the important correlations of input data. Distance metric learning is defined as learning an appropriate similarity or distance metric fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cd144f3f731ec5d09c1122f8304a45e
https://doi.org/10.1016/j.neucom.2018.08.071
https://doi.org/10.1016/j.neucom.2018.08.071
Publikováno v:
Applied Intelligence. 48:755-770
Recently, two-dimensional canonical correlation analysis (2DCCA) has been successfully applied for image feature extraction. The method instead of concatenating the columns of the images to the one-dimensional vectors, directly works with two-dimensi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6aeac3b651b070e8a7961e73eb6ba67
https://doi.org/10.1007/s10489-017-1012-2
https://doi.org/10.1007/s10489-017-1012-2
Publikováno v:
Knowledge-Based Systems. 223:107025
Many reinforcement learning problems are hierarchical in nature. Exploiting this property can ease the learning process. In this paper, a hierarchical policy search method based on clustering is presented. We use a hierarchical policy which is compos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f7ef91eec5da95744402698e44e5815
https://doi.org/10.1016/j.knosys.2021.107025
https://doi.org/10.1016/j.knosys.2021.107025