Tarasiuk, PawełPryczek, Michał2021-07-152021-07-152016Tarasiuk, P., & Pryczek, M. (2016). Geometric Transformations Embedded into Convolutional Neural Networks. Journal of Applied Computer Science, 24(3), 33-48. https://doi.org/10.34658/jacs.2016.24.3.33-481507-0360http://hdl.handle.net/11652/3850https://doi.org/10.34658/jacs.2016.24.3.33-48This paper presents a novel extension to convolutional neural networks. While CNNs are known for invariance to object translation, changes to the other parameters could make the image recognition tasks diffcult – that includes rotations and scaling. Some improvement in this area could be achieved with embedded geometric transformations used inside the CNNs. In order to provide a practical solution, which allows fast propagation and learning of the modified networks, “fast geometric transformations” are introduced.enFair use conditionDla wszystkich w zakresie dozwolonego użytkuartificial intelligencemachine learningdeep learningconvolutional neural networksimage processingimage recognitiongeometric transformationssztuczna inteligencjanauczanie maszynowegłęboka naukasplotowe sieci neuronoweprzetwarzanie obrazurozpoznawanie obrazuprzekształcenia geometryczneArtykułLUT LicenseLicencja PŁhttps://doi.org/10.34658/jacs.2016.24.3.33-4810.34658/jacs.2016.24.3.33-48