U
Umut Güçlü
Researcher at Radboud University Nijmegen
Publications - 87
Citations - 2524
Umut Güçlü is an academic researcher from Radboud University Nijmegen. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 22, co-authored 79 publications receiving 1879 citations. Previous affiliations of Umut Güçlü include Nijmegen Institute for Cognition and Information & Open University of Catalonia.
Papers
More filters
Journal ArticleDOI
Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
TL;DR: It is quantitatively shown that there indeed exists an explicit gradient for feature complexity in the ventral pathway of the human brain, and this provides strong support for the hypothesis that object categorization is a guiding principle in the functional organization of the primate ventral stream.
Journal ArticleDOI
Increasingly complex representations of natural movies across the dorsal stream are shared between subjects
TL;DR: Results show that a DNN trained for action recognition can be used to accurately predict how dorsal stream responds to natural movies, revealing a correspondence in representations of DNN layers and dorsal stream areas, suggesting that a common representational space underlies dorsal stream responses across multiple subjects.
Journal ArticleDOI
Generative adversarial networks for reconstructing natural images from brain activity
TL;DR: A method for reconstructing visual stimuli from brain activity using a deep convolutional generative adversarial network capable of generating gray scale photos, similar to stimuli presented during two functional magnetic resonance imaging experiments is explored.
Journal ArticleDOI
Modeling the Dynamics of Human Brain Activity with Recurrent Neural Networks.
TL;DR: It is shown that the proposed recurrent neural network models can significantly outperform established response models by accurately estimating long-term dependencies that drive hemodynamic responses.
Journal ArticleDOI
Convolutional neural network-based encoding and decoding of visual object recognition in space and time.
K. Seeliger,Matthias Fritsche,Umut Güçlü,Sanne Schoenmakers,Jan-Mathijs Schoffelen,Sander E. Bosch,M.A.J. van Gerven +6 more
TL;DR: This work combines CNN‐based encoding models with magnetoencephalography to validate the accuracy of the encoding model by decoding stimulus identity in a left‐out validation set of viewed objects, achieving state‐of‐the‐art decoding accuracy.