Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jiun-Der You"'
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 5915-5928 (2020)
Perceptron is adopted to classify the Ricker wavelets and to detect the seismic anomaly in a seismogram. Three learning rules are used in the training of perceptron to solve the decision boundary. The optimal learning-rate parameter is derived. The l
Externí odkaz:
https://doaj.org/article/c576d94494634d77b6cac9b5f94f9bc8
Publikováno v:
IGARSS
In the multilayer perceptron (MLP), there was a theorem about the maximum number of separable regions (M) given the number of hidden nodes (H) in the input d-dimensional space. We propose a recurrence relation to prove the theorem using the expansion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba7a107b0be32ee452243e0f8a141dcf
https://doi.org/10.1109/igarss.2016.7729721
https://doi.org/10.1109/igarss.2016.7729721
Publikováno v:
Neurocomputing. 71:3264-3274
Hough transform neural network is adopted to detect the line pattern of direct wave and the hyperbolic pattern of reflection wave in a one-shot seismogram. We use time difference from point to hyperbola and line as the distance in the pattern detecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a485f480de2fc35a5eaac536ffd16ac
https://doi.org/10.1016/j.neucom.2008.04.034
https://doi.org/10.1016/j.neucom.2008.04.034
Publikováno v:
IJCNN
In the multilayer perceptron (MLP), there was a theorem about the maximum number of separable regions (M) given the number of hidden nodes (H) in the input d-dimensional space. We propose a recurrence relation in the high dimensional space and prove
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce358c353166d905fff73156c716c386
https://doi.org/10.1109/ijcnn.2015.7280447
https://doi.org/10.1109/ijcnn.2015.7280447
Publikováno v:
2015 25th International Conference on Field Programmable Logic & Applications (FPL); 2015, p1-6, 6p