Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Mikko Lehtokangas"'
Publikováno v:
Neurocomputing. 61:339-360
Neural networks have been studied for channel equalization purposes with quite promising results. However, not a lot of published results are available for their performance in realistic mobile systems, such as Global System for Mobile communications
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4b58f8fc6b9d916bf2eb780234de611
https://doi.org/10.1016/j.neucom.2003.11.007
https://doi.org/10.1016/j.neucom.2003.11.007
Publikováno v:
Neurocomputing. 56:345-363
We have investigated four constructive neural network algorithms for evaluating the movements of a robotic manipulator. During the course of the study, the algorithms were improved by merging regularization approach and architectural flexibility into
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd1917013bc1aad7edd371d390ebbeed
https://doi.org/10.1016/j.neucom.2003.03.001
https://doi.org/10.1016/j.neucom.2003.03.001
Publikováno v:
Neurocomputing. 48:573-607
In this study, we have investigated five different constructive neural network algorithms, of which four were methods found in the literature and one was our own recently developed algorithm. The algorithms that were studied were Cascade-Correlation,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c529507e2f6cfcf565ef380c85d5069
https://doi.org/10.1016/s0925-2312(01)00630-0
https://doi.org/10.1016/s0925-2312(01)00630-0
Autor:
Jukka Saarinen, Mikko Lehtokangas, Joel Hasan, Alpo Värri, Eero Huupponen, Sari-Leena Himanen
Publikováno v:
Neuropsychobiology. 45:99-105
In the present work, gender differences in sleep spindle topography were examined in 40 subjects. Their median age was 32 years (range 22–49 years). Spindles were detected from 3,306,060 s of visually scored stage 2 sleep EEG by a previously valida
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f25bec10ee44d9d79acccf2da4d67f61
https://doi.org/10.1159/000048684
https://doi.org/10.1159/000048684
Autor:
Mikko Lehtokangas
Publikováno v:
Neurocomputing. 35:113-122
Choosing a network size is a difficult problem in neural network modelling. In many recent studies constructive or destructive methods that add or delete connections, neurons, layers have been studied for solving this problem. In this work, we consid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3323df626680b90bf9d07284638c2dfd
https://doi.org/10.1016/s0925-2312(00)00304-0
https://doi.org/10.1016/s0925-2312(00)00304-0
Autor:
Mikko Lehtokangas
Publikováno v:
International Journal of Pattern Recognition and Artificial Intelligence. 14:211-223
A hybrid neural network architecture is investigated for classification purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers the first hidden layer is selected to be an adaptive cen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25d205b3309873f4b29a4079d3d85b3f
https://doi.org/10.1142/s0218001400000143
https://doi.org/10.1142/s0218001400000143
Publikováno v:
Journal of Medical Systems. 24:183-193
Spindles are one of the most important short-lasting waveforms in sleep EEG. They are the hallmarks of the so-called Stage 2 sleep. Visual spindle scoring is a tedious workload, since there are often a thousand spindles in one all-night recording of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1050799e63ead85526337217650bdd6a
https://doi.org/10.1023/a:1005543710588
https://doi.org/10.1023/a:1005543710588
Publikováno v:
Information Sciences. 121:171-199
During this decade voice dialling has became a potential feature to be implemented, e.g., in the mobile phones, but the techniques still suffer from defects of current algorithms when a real background noise is present. In this paper, a hybrid speech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fedbec4984a39a63675d47a0126e2c42
https://doi.org/10.1016/s0020-0255(99)00077-8
https://doi.org/10.1016/s0020-0255(99)00077-8
Autor:
Mikko Lehtokangas
Publikováno v:
International Journal of Neural Systems. :1-9
A hybrid neural network architecture is investigated for modeling purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers, the first hidden layer is selected to be an adaptive referenc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::116c2015822540c6e530bd8b003b70f1
https://doi.org/10.1142/s0129065799000022
https://doi.org/10.1142/s0129065799000022
Autor:
Mikko Lehtokangas
Publikováno v:
Neural Processing Letters. 9:271-278
Choosing a network size is a difficult problem in neural network modelling. In many recent studies, constructive or destructive methods that add or delete connections, neurons or layers have been studied in order to solve this problem. In this work w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a9502a0be06363aa1b0855234edfca3
https://doi.org/10.1023/a:1018620424763
https://doi.org/10.1023/a:1018620424763