arXiv subjects

Umut Güçlü

Publications and source records attributed to Umut Güçlü.

23 records · Page 2Linked to original sources

arXiv2016

Convolutional Sketch Inversion

In this paper, we use deep neural networks for inverting face sketches to synthesize photorealistic face images. We first construct a semi-simulated dataset containing a very large number of computer-generated face sketches with different styles and corresponding face images by expanding existing unconstrained face data sets. We then train models achieving state-of-the-art results on both computer-generated sketches and hand-drawn sketches by leveraging recent advances in deep learning such as batch normalization, deep residual learning, perceptual losses and stochastic optimization in combination with our new dataset. We finally demonstrate potential applications of our models in fine arts and forensic arts. In contrast to existing patch-based approaches, our deep-neural-network-based approach can be used for synthesizing photorealistic face images by inverting face sketches in the wild.

cs.CV↗

arXiv2016

Modeling the dynamics of human brain activity with recurrent neural networks

Encoding models are used for predicting brain activity in response to sensory stimuli with the objective of elucidating how sensory information is represented in the brain. Encoding models typically comprise a nonlinear transformation of stimuli to features (feature model) and a linear transformation of features to responses (response model). While there has been extensive work on developing better feature models, the work on developing better response models has been rather limited. Here, we investigate the extent to which recurrent neural network models can use their internal memories for nonlinear processing of arbitrary feature sequences to predict feature-evoked response sequences as measured by functional magnetic resonance imaging. We show that the proposed recurrent neural network models can significantly outperform established response models by accurately estimating long-term dependencies that drive hemodynamic responses. The results open a new window into modeling the dynamics of brain activity in response to sensory stimuli.

q-bio.NC↗

arXiv2016

Brains on Beats

We developed task-optimized deep neural networks (DNNs) that achieved state-of-the-art performance in different evaluation scenarios for automatic music tagging. These DNNs were subsequently used to probe the neural representations of music. Representational similarity analysis revealed the existence of a representational gradient across the superior temporal gyrus (STG). Anterior STG was shown to be more sensitive to low-level stimulus features encoded in shallow DNN layers whereas posterior STG was shown to be more sensitive to high-level stimulus features encoded in deep DNN layers.

q-bio.NC↗

arXiv2015

Semantic vector space models predict neural responses to complex visual stimuli

Encoding models have as their objective to predict neural responses to naturalistic stimuli with the aim of elucidating how sensory information is represented in the brain. This prediction is achieved by representing the stimulus in terms of a suitable feature space and using this feature space to linearly predict observed neural responses. Here, we investigate to what extent semantic vector space models can be used to predict neural responses to complex visual stimuli. We show that these models provide good predictions of neural responses in downstream visual areas, improving significantly over a low-level control model based on Gabor wavelet pyramids. The outlined approach provides a new way to model and map high-level semantic representations across cortex.

q-bio.NC↗

arXiv2014

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway

Converging evidence suggests that the mammalian ventral visual pathway encodes increasingly complex stimulus features in downstream areas. Using deep convolutional neural networks, we can now quantitatively demonstrate that there is indeed an explicit gradient for feature complexity in the ventral pathway of the human brain. Our approach also allows stimulus features of increasing complexity to be mapped across the human brain, providing an automated approach to probing how representations are mapped across the cortical sheet. Finally, it is shown that deep convolutional neural networks allow decoding of representations in the human brain at a previously unattainable degree of accuracy, providing a more sensitive window into the human brain.

q-bio.NC↗