Browsing by Author "Yarman-Vural, F. T."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    An energy efficient additive neural network
    (IEEE, 2017) Afrasiyabi, A.; Nasir, B.; Yıldız, O.; Yarman-Vural, F. T.; Çetin, A. Enis
    In this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the 'product' of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This 'product' is used to construct a vector product in n-dimensional Euclidean space. The vector product induces the lasso norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron.
  • Thumbnail Image
    ItemOpen Access
    Joint dictionary learning reconstruction of compressed multi-contrast magnetic resonance imaging
    (Institute of Electrical and Electronics Engineers, 2018) Güngör, A.; Kopanoğlu, E.; Çukur, Tolga; Güven, E.; Yarman-Vural, F. T.
    This study deals with reconstruction of compressed multicontrast magnetic resonance image (MRI) reconstruction using joint dictionary learning. Usually pre-determined dictionaries are used for compressed sensing reconstructions. Here, we propose an alternating-minimization based algorithm for recovering image and sparsifying transformation from only data itself. The proposed method can also be viewed as a joint multicontrast reconstruction extension of a previous blind compressive sensing algorithm [1]. For evaluation, the algorithm is compared in terms of convergence speed and image quality to both individual dictionary learning based method [1], and a joint reconstruction algorithm using pre-determined dictionaries for MRI [2].