Reconstructing Perceived Faces from Brain Activations with Deep Adversarial Neural Decoding
Abstract
Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the nonlinear transformation from perceived stimuli to latent features with adversarial training of convolutional neural networks. We test our approach with a functional magnetic resonance imaging experiment and show that it can generate state-of-the-art reconstructions of perceived faces from brain activations.
Cite
Text
Güçlütürk et al. "Reconstructing Perceived Faces from Brain Activations with Deep Adversarial Neural Decoding." Neural Information Processing Systems, 2017.Markdown
[Güçlütürk et al. "Reconstructing Perceived Faces from Brain Activations with Deep Adversarial Neural Decoding." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/gucluturk2017neurips-reconstructing/)BibTeX
@inproceedings{gucluturk2017neurips-reconstructing,
title = {{Reconstructing Perceived Faces from Brain Activations with Deep Adversarial Neural Decoding}},
author = {Güçlütürk, Yağmur and Güçlü, Umut and Seeliger, Katja and Bosch, Sander and van Lier, Rob and van Gerven, Marcel A. J.},
booktitle = {Neural Information Processing Systems},
year = {2017},
pages = {4246-4257},
url = {https://mlanthology.org/neurips/2017/gucluturk2017neurips-reconstructing/}
}