Filters








35 Hits in 7.8 sec

Dissociable neural representations of adversarially perturbed images in convolutional neural networks and the human brain [article]

Chi Zhang, Xiaohan Duan, Linyuan Wang, Yongli Li, Bin Yan, Guoen Hu, Ruyuan Zhang, Li Tong
2020 arXiv   pre-print
Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences  ...  We use functional magnetic resonance imaging to measure brain activity evoked by regular and adversarial images in the human brain, and compare it to the activity of artificial neurons in a prototypical  ...  All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (Henan Provincial People's Hospital) and with the Helsinki Declaration of 1975  ... 
arXiv:1812.09431v3 fatcat:k4ps4yljcbexthcul4r36gmahy

Not-So-CLEVR: learning same–different relations strains feedforward neural networks

Junkyung Kim, Matthew Ricci, Thomas Serre
2018 Interface Focus  
As a prime example, convolutional neural networks (CNNs), a type of 3 feedforward neural network, now approach human accuracy on visual recognition tasks like image 4 classification (He et al., 2015) and  ...  We systematically study the ability of feedforward 9 neural networks to learn to recognize a variety of visual relations and demonstrate that same-different 10 visual relations pose a particular strain  ...  One prominent example 484 is adversarial perturbation (Goodfellow et al., 2015), a type of structured image distortion that 485 asymmetrically affects CNNs and humans.  ... 
doi:10.1098/rsfs.2018.0011 pmid:29951191 fatcat:is66kbtqn5felazo2lxifbuxmy

Artistic Style Meets Artificial Intelligence

Suk Kyoung Choi, Steve DiPaola, Hannu Töyrylä
2021 Journal of Perceptual Imaging  
Recent developments in neural network image processing motivate the question, how these technologies might better serve visual artists.  ...  In this article, the authors explore the phenomenology of the creative environment afforded by artificially intelligent image transformation and generation, drawn from autoethnographic reviews of the authors  ...  ACKNOWLEDGMENT This research has been partially supported by Social Sciences & Humanities Research Council of Canada (SSHRC).  ... 
doi:10.2352/j.percept.imaging.2021.4.3.030501 fatcat:anzr6fckwzampmz73lbwvl5vda

Artistic Style Meets Artificial Intelligence

Suk Kyoung Choi, Steve DiPaola, Hannu Töyrylä
2021 Journal of Perceptual Imaging  
Recent developments in neural network image processing motivate the question, how these technologies might better serve visual artists.  ...  In this article, the authors explore the phenomenology of the creative environment afforded by artificially intelligent image transformation and generation, drawn from autoethnographic reviews of the authors  ...  A computational metamorphosis of the image derives from high-level statistical sampling and convolution of input data. Human semantics are reframed as algorithmic potentialities.  ... 
doi:10.2352/j.percept.imaging.2021.4.2.020501 fatcat:qdo4b7gc2nehphsxtcvaun7dbu

The neural code for 'face cells' is not face specific [article]

Kasper Vinken, Talia Konkle, Margaret Livingstone
2022 bioRxiv   pre-print
The relationship between category-level face selectivity and image-level non-face tuning was not predicted by color and simple shape properties, but by domain-general information encoded in deep neural  ...  Analyzing neural responses in and around macaque face patches to hundreds of objects, we discovered graded tuning for non-face objects that was more predictive of face preference than was tuning for faces  ...  by statistical regularities encoded in convolutional deep neural networks (DNNs).  ... 
doi:10.1101/2022.03.06.483186 fatcat:brhypoemxnbczayurz2srcvg2m

Modern Views of Machine Learning for Precision Psychiatry [article]

Zhe Sage Chen, Prathamesh Kulkarni, Isaac R. Galatzer-Levy, Benedetta Bigio, Carla Nasca, Yu Zhang
2022 arXiv   pre-print
We further discuss explainable AI (XAI) and causality testing in a closed-human-in-the-loop manner, and highlight the ML potential in multimedia information extraction and multimodal data fusion.  ...  In light of the NIMH's Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and  ...  Acknowledgments The research was partially supported from the US National Science Foundation (CBET-1835000 to Z.S.C.), the National Institutes of Health (R01-NS121776 and R01-MH118928 to Z.S.C.).  ... 
arXiv:2204.01607v2 fatcat:coo557v2jzh6debycy3mhccfze

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

Eric M. Christiansen, Samuel J. Yang, D. Michael Ando, Ashkan Javaherian, Gaia Skibinski, Scott Lipnick, Elliot Mount, Alison O'Neil, Kevan Shah, Alicia K. Lee, Piyush Goyal, William Fedus (+6 others)
2018 Cell  
However, these approaches have significant drawbacks, including inconsistency; limitations in the number of simultaneous labels because of spectral overlap; and necessary perturbations of the experiment  ...  ISL predicts a range of labels, such as those for nuclei, cell type (e.g., neural), and cell state (e.g., cell death).  ...  In that case, one would probably want to use 3D convolutions rather than 2D convolutions in the neural network. 2.  ... 
doi:10.1016/j.cell.2018.03.040 pmid:29656897 pmcid:PMC6309178 fatcat:wasznnjeufdeho6h3fry7qvdj4

Deep learning for radar data exploitation of autonomous vehicle [article]

Arthur Ouaknine
2022 arXiv   pre-print
The redundancy and complementarity of the vehicle's sensors provide an accurate and robust comprehension of the environment, thereby increasing the level of performance and safety.  ...  With the rapid progress of deep learning and the availability of public driving datasets, the perception ability of vision-based driving systems has considerably improved.  ...  I would like to thank the jury of my thesis for your time and your relevant feedbacks which truly improved the quality of this thesis.  ... 
arXiv:2203.08038v1 fatcat:zjupxkpaffgavm45oqpwnhkczq

Past, Present, and Future of EEG-Based BCI Applications

Kaido Värbu, Naveed Muhammad, Yar Muhammad
2022 Sensors  
An electroencephalography (EEG)-based brain–computer interface (BCI) is a system that provides a pathway between the brain and external devices by interpreting EEG.  ...  The distribution of the research between the medical and non-medical domain has been analyzed and further categorized into fields of research within the reviewed domains.  ...  , big mistakes: adversarial perturbations induce errors in brain-computer interface spellers Zolfaghari et al. 2021 Using convolution neural networks pattern for classification of motor imagery in bci  ... 
doi:10.3390/s22093331 pmid:35591021 pmcid:PMC9101004 fatcat:gn6bt4uqavenzbu3nkt32de42m

DynaMorph: learning morphodynamic states of human cells with live imaging and sc-RNAseq [article]

Zhenqin Wu, Bryant B. Chhun, Galina Schmunk, Chang Kim, Li-Hao Yeh, Tomasz J. Nowakowski, James Zou, Shalin B. Mehta
2020 bioRxiv   pre-print
Morphological states of human cells are widely imaged and analyzed to diagnose diseases and to discover biological mechanisms.  ...  As a case study, we apply DynaMorph to study the morphodynamic states of live primary human microglia, which are mobile immune cells of the brain that exhibit complex functional states.  ...  Acknowledgements We thank Syuan-Ming Guo for discussions around machine learning and dimensionality reduction. We thank Greg Huber for discussions around the physical models of cell states.  ... 
doi:10.1101/2020.07.20.213074 fatcat:yw3fdjiwdrhhpca6b6i63btshe

2022 Review of Data-Driven Plasma Science [article]

Rushil Anirudh, Rick Archibald, M. Salman Asif, Markus M. Becker, Sadruddin Benkadda, Peer-Timo Bremer, Rick H.S. Budé, C.S. Chang, Lei Chen, R. M. Churchill, Jonathan Citrin, Jim A Gaffney (+51 others)
2022 arXiv   pre-print
Despite the recent impressive progress in applications of data science to plasma science and technology, the emerging field of DDPS is still in its infancy.  ...  This review article highlights latest development and progress in the interdisciplinary field of data-driven plasma science (DDPS).  ...  In comparison, there are about 100 billion neurons in a human brain. Most parameters of a neural network called weights are determined during the training process.  ... 
arXiv:2205.15832v1 fatcat:fxsl6gl3fncnhpoj76defxoc3a

Predictive Coding: a Theoretical and Experimental Review [article]

Beren Millidge, Anil Seth, Christopher L Buckley
2022 arXiv   pre-print
The theory is closely related to the Bayesian brain framework and, over the last two decades, has gained substantial influence in the fields of theoretical and cognitive neuroscience.  ...  plausibility for implementation in the brain and the concrete neurophysiological and psychological predictions made by the theory.  ...  Acknowledgements We would like to thanks Alexander Tschantz, Conor Heins, and Rafal Bogacz for useful discussions about this manuscript and on predictive coding in general.  ... 
arXiv:2107.12979v4 fatcat:wfzvlaek7zbfhnhda4ljxuvyh4

Artificial Intelligence in Translational Medicine

Simone Brogi, Vincenzo Calderone
2021 International Journal of Translational Medicine  
in breakthroughs for advancing human health.  ...  The huge advancement in Internet web facilities as well as the progress in computing and algorithm development, along with current innovations regarding high-throughput techniques, enable the scientific  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijtm1030016 fatcat:c6g6ld26gjg6jbkcddauo44qvu

Towards Explainable Fact Checking [article]

Isabelle Augenstein
2021 arXiv   pre-print
The past decade has seen a substantial rise in the amount of mis- and disinformation online, from targeted disinformation campaigns to influence politics, to the unintentional spreading of misinformation  ...  As deep neural networks are black-box models, their inner workings cannot be easily explained.  ...  Chen et al. 2017 used convolutional neural networks (CNN) for obtaining the representation of each tweet, assigned a probability for a class by a softmax classifier and Garcı́a Lozano et al. 2017 used  ... 
arXiv:2108.10274v2 fatcat:5s4an6irezcjfmvvhmiaeqarh4

Automated Deep Learning: Neural Architecture Search Is Not the End [article]

Xuanyi Dong, David Jacob Kedziora, Katarzyna Musial, Bogdan Gabrys
2022 arXiv   pre-print
This endeavor seeks to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS), a topic that has been the focus of several surveys.  ...  Moreover, each of these steps typically relies heavily on humans, in terms of both knowledge and interactions, which impedes the further advancement and democratization of DL.  ...  Acknowledgments: XD and DJK acknowledge financial support secured by BG, which funded their participation in this study and the ongoing "Automated and Autonomous Machine Learning" project as part of the  ... 
arXiv:2112.09245v3 fatcat:dujfh7pzmzbrtdyoshkl4kpbsm
« Previous Showing results 1 — 15 out of 35 results