The DOI matches its Crossref record; 27 of the 28 references it cites were found in a registry or an index.
İLERİ-GERİ TAKİP ALGORİTMASI TABANLI SEYREK AŞIRI ÖĞRENME MAKİNESİ
Open accessAbstract
Son zamanlarda, Aşırı Öğrenme Makinaları (AÖM) makine öğrenmesi alanında ilgi duyulan bir konu haline gelmiştir.AÖM Tek Gizli Katmanlı İleri Beslemeli (TGKİB) ağlar için önerilmiş yeni bir öğrenme algoritmasıdır.AÖM modeli iyi genelleme performansı, aşırı hızlı öğrenme yeteneği ve düşük işlem karmaşıklığı gibi avantajlara sahiptir.Bu avantajlarının yanı sıra, AÖM bazı dezavantajlara sahiptir.Öncelikle, çıkış ağırlıklarının hesaplanmasında en küçük kareler minimizasyonu kullanıldığından aşırı örtüşme ile karşı karşıyadır.Bir diğer sakınca ise AÖM'nin doğruluğunun gizli katman nöron sayısına bağlı olmasıdır.Bu olumsuzluk geniş ölçekli problemlerde daha kötü bir hal almaktadır.Çalışmamızda, bu olumsuzlukları gidermek için seyrek tabanlı bir AÖM modeli önerildi.Seyrek tabanlı AÖM modelinde, çıkış ağırlıklarının seyrek temsilini hesaplamak için yinelemeli fırsatçı takip algoritması tabanlı İleri-Geri Takip (İGT) algoritması kullanılmıştır.İGT-AÖM olarak adlandırılan yöntem normal AÖM ile karşılaştırıldığında aşırı örtüşmeyen (ezberlemeyen) ağ yapısı, düşük hesap karmaşıklığı ve gizli katman nöronlarının kabul edilebilir bir sayıda olması gibi üstünlüklere sahiptir.Yaygın kullanılan sınıflandırma problemleri üzerine yapılan deneysel çalışmalar ışığında İGT-AÖM yöntemi dikkate değer üstünlükler göstermektedir.Ayrıca başarımın etkinliğini vurgulamak için çalışmanın devamında normal AÖM ve en küçük açısal regresyon (Least angle regression, LARS), en küçük mutlak daralma ve seçme operatörü (Least absolute shrinkage and selection operator, LASSO) ve Elastic Net gibi düzenlenmiş AÖM'ler ile önerilen metodun karşılaştırılması yapılmıştır.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“İki vektörün benzerliği (spectral angle) metodu ile Öklit uzaklığına göre daha iyi hızlanma sağlanmıştır.”
From GPU Programlamada CUDA Platformu Kullanılan Paralel Görüntü İşleme Çalışmalarının İncelenmesi (2020) · cites this paper as [87]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 24,190
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Extreme learning machine: Theory and applications
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006) · Neurocomputing · doi:10.1016/j.neucom.2005.12.126 · Cited by 13,285
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Extreme Learning Machine for Regression and Multiclass Classification
Huang, G.-B., Zhou, H., Ding, X., & Zhang, R. (2011) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2011.2168604 · Cited by 5,575
Greed is Good: Algorithmic Results for Sparse Approximation
Tropp, J. A. (2004) · IEEE Transactions on Information Theory · doi:10.1109/tit.2004.834793 · Cited by 3,624
Generalized Inverse of Matrices and Its Applications
Banerjee, K. S., Rao, C. R., & Mitra, S. K. (1973) · Technometrics · doi:10.1080/00401706.1973.10489026 · Cited by 2,320
Kivinen, J., Smola, A. J., & Williamson, R. C. (2004) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2004.830991 · Cited by 1,021
Computational Methods for Sparse Solution of Linear Inverse Problems
Tropp, J., & Wright, S. J. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2044010 · Cited by 991
OP-ELM: Optimally Pruned Extreme Learning Machine
Miché, Y., Sorjamaa, A., Bas, P., Simula, O., Jutten, C., & Lendasse, A. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2009.2036259 · Cited by 763
Regularized Extreme Learning Machine
Deng, W., Zheng, Q., & Lin, C. (2009) · IEEE Symposium on Computational Intelligence and Data Mining (CIDM) · doi:10.1109/cidm.2009.4938676 · Cited by 460
Incremental extreme learning machine with fully complex hidden nodes
Huang, G.-B., Li, M.-B., Chen, L., & Siew, C. (2007) · Neurocomputing · doi:10.1016/j.neucom.2007.07.025 · Cited by 259
TROP-ELM: A double-regularized ELM using LARS and Tikhonov regularization
Miché, Y., van Heeswijk, M., Bas, P., Simula, O., & Lendasse, A. (2011) · Neurocomputing · doi:10.1016/j.neucom.2010.12.042 · Cited by 224
Regularized extreme learning machine for regression problems
Martínez-Martínez, J. M., Escandell-Montero, P., Soria‐Olivas, E., Martín‐Guerrero, J. D., Magdalena‐Benedito, R., & Gómez‐Sanchís, J. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.06.013 · Cited by 209
Sparse Bayesian Extreme Learning Machine for Multi-classification
Luo, J., Vong, C., & Wong, P. K. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2281839 · Cited by 193
Computational Methods for Sparse Solution of Linear Inverse Problems
Tropp, J. A., & Wright, S. J. (2009) · doi:10.21236/ada633835 · Cited by 127
Luo, M., & Zhang, K. (2013) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2013.05.012 · Cited by 89
Compressed sensing signal recovery via forward–backward pursuit
Karahanoğlu, N. B., & Erdoğan, H. (2013) · Digital Signal Processing · doi:10.1016/j.dsp.2013.05.007 · Cited by 87
Greedy Algorithms andM-Term Approximation with Regard to Redundant Dictionaries
Temlyakov, V. N. (1999) · Journal of Approximation Theory · doi:10.1006/jath.1998.3265 · Cited by 86
Topics in Compressed SensingPreprint
Needell, D. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0905.4482 · Cited by 65
Model-Based Online Learning With Kernels
Li, G., Wen, C., Li, Z. G., Zhang, A., Yang, F., & Mao, K. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2229293 · Cited by 54
Generalized Inverse of Matrices and Its Applications
Banerjee, K. S., Rao, C. R., & Mitra, S. K. (1973) · Technometrics · doi:10.2307/1266840 · Cited by 54
GA-SELM: Greedy algorithms for sparse extreme learning machine
Alçin, Ö. F., Şengür, A., Ghofrani, S., & İnce, M. C. (2014) · Measurement · doi:10.1016/j.measurement.2014.04.012 · Cited by 36
Self-citationOMP-ELM: Orthogonal Matching Pursuit-Based Extreme Learning Machine for Regression
Alçin, Ö. F., Şengür, A., Qian, J., & İnce, M. C. (2014) · Journal of Intelligent Systems · doi:10.1515/jisys-2014-0095 · Cited by 14
Self-citationEMG signal classification by extreme learning machine
Ertuğrul, Ö. F., Tagluk, M. E., Kaya, Y., & Teki̇n, R. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531269 · Cited by 12
Comparison of iterative sparse recovery algorithms
Karakuş, C., & Gürbüz, A. C. (2011) · IEEE Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2011.5929786 · Cited by 11
Optimal forward-backward pursuit for the sparse signal recovery problem
Karahanoğlu, N. B., & Erdoğan, H. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531595 · Cited by 2
Cited by
Sorted by citations
Türkoğlu, M., & Hanbay, D. (2019) · Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi · doi:10.17341/gazimmfd.423674 · Cited by 4
GPU Programlamada CUDA Platformu Kullanılan Paralel Görüntü İşleme Çalışmalarının İncelenmesi
AYDIN, S., SAMET, R., & BAY, Ö. F. (2020) · Politeknik Dergisi · doi:10.2339/politeknik.563767 · Cited by 3
“Topıcs In Applıed Earth Observatıons And Remote Sensıng, 8 (6): 2884-2893, (2015) [89] Alçin Ö.”
Metadata
- Authors
- ALÇİN, Ö. F., ŞENGÜR, A., & İNCE, M. C.
- Venue
- Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi
- Published
- 2015-03-31
- Volume
- 30
- Issue
- 1
- ISSN
- 1300-1884 (ISSN-L)
- 1304-4915
- OpenAlex
- W1875411448
- Cited by
- 2
- References
- 28
- Citations by year
- 2019: 2
- FWCI
- 0.00
- Type
- journal article
- Language
- tr
- Open access
- bronze
- doi.org
- Locations
- Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi (publishedVersion)
- DergiPark (Istanbul University) (submittedVersion)
- DSpace - FIRAT (Fırat University) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- extreme learning machine, overfitting, sparse representation, classification, least angle regression, LASSO, elastic net, regularization, hidden neuron number, computational complexity, generalization performance, small sample size problem, high-dimensional problems, feature selection, dimensionality reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
