Calisan, MucahitTalu, M. Fatih2024-08-042024-08-042017978-1-5386-1880-6https://hdl.handle.net/11616/980952017 International Artificial Intelligence and Data Processing Symposium (IDAP) -- SEP 16-17, 2017 -- Malatya, TURKEYIn this study, artificial learning approach which can express high dimensional data in a lower space (autocoding) and known as autoencoder in the literature has been investigated in detail without using a predefined ready mathematical model. The most important feature of this method, which can be used in place of traditional feature extraction methods (HOG, SHIFT, SURF, Wavelet, etc.), is the ability to extract data-specific features. By applying the real (MNIST) and synthetic data, the effects on the success of the parameters of the method are measured and the results are presented in a tabular form.trinfo:eu-repo/semantics/closedAccessDeep learningautoencoderfeature extractionfeature selectiondata reductiondimension reductionConference Object2-s2.0-85039920699N/AWOS:000426868700110N/A