1,548 Hits in 6.5 sec

Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI [article]

Georgia Koppe, Hazem Toutounji, Peter Kirsch, Stefanie Lis, Daniel Durstewitz
2019 arXiv   pre-print
Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data.  ...  In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems  ...  In contrast, recurrent neural networks (RNNs) represent a class of nonlinear DS models which are universal in the sense that they can approximate arbitrarily closely the flow of any other dynamical system  ... 
arXiv:1902.07186v2 fatcat:oduv5aiezffyxbu7bk2kt4hz3y

Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI

Georgia Koppe, Hazem Toutounji, Peter Kirsch, Stefanie Lis, Daniel Durstewitz, Leyla Isik
2019 PLoS Computational Biology  
Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data.  ...  In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems  ...  via generative RNNs with applications to fMRI .  ... 
doi:10.1371/journal.pcbi.1007263 pmid:31433810 pmcid:PMC6719895 fatcat:rzp5qcndmnfw7av4v4yrnhgmr4

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
in Trauma Interventions 753 Multimodal Recurrent Model with Attention for Automated Radiology Report Generation 754 Structured Deep Generative Model of FMRI Signals for Mental Disorder Diagnosis 758 The  ...  tumor segmentation in MRI 572 Inherent Brain Segmentation Quality Control from Fully ConvNet Monte-Carlo Sampling 573 Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN) 577  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Guest Editorial Learning in Neuromorphic Systems and Cyborg Intelligence

Zhaohui Wu, Ryad Benosman, Huajin Tang, Shih-Chii Liu
2017 IEEE Transactions on Neural Networks and Learning Systems  
multiple timescale recurrent neural network to develop different behavior generation schemes, such as sensory reflex and intentional proactive behaviors.  ...  The fifth paper, entitled Learning to perceive the world as probabilistic or deterministic via interaction with others: A neuro-robotics experiment, develops a dynamic neural network model, named as stochastic  ...  Benosman was awarded with the National Best French Scientific Paper by the Journal La Recherche for his work on neuromorphic retinas and their applications to retina stimulation and prosthetics in 2013  ... 
doi:10.1109/tnnls.2017.2650599 fatcat:ww34h4veofg6zky6w76mtlqkke

Learning Brain Dynamics with Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks

Germán Abrevaya, Guillaume Dumas, Aleksandr Y. Aravkin, Peng Zheng, Jean-Christophe Gagnon-Audet, James Kozloski, Pablo Polosecki, Guillaume Lajoie, David Cox, Silvina Ponce Dawson, Guillermo Cecchi, Irina Rish
2021 Neural Computation  
On the other hand, generic nonlinear models such as deep recurrent neural networks often require large amounts of training data, not always available in domains such as brain imaging; also, they often  ...  Finally, we demonstrate that our (generative) VDP model can also serve as a data-augmentation tool leading to marked improvements in predictive accuracy of recurrent neural networks.  ...  Dynamical modeling was applied to nonlinear systems early on by Anderson and Moore (1979) and Mortensen (1968) .  ... 
doi:10.1162/neco_a_01401 pmid:34310676 fatcat:v7pv3no2njfkxp5oitmwllzs5m

Is the brain macroscopically linear? A system identification of resting state dynamics [article]

Erfan Nozari, Maxwell A. Bertolero, Jennifer Stiso, Lorenzo Caciagli, Eli J. Cornblath, Xiaosong He, Arun S. Mahadevan, George J. Pappas, Dani Smith Bassett
2021 arXiv   pre-print
Our results, together with the unparalleled interpretability of linear models, can greatly facilitate our understanding of macroscopic neural dynamics and the principled design of model-based interventions  ...  of system identification.  ...  Nonlinear models via long short-term memory neural networks ('LSTM (IIR)', 'LSTM (FIR)'): The above DNN models are inherently static (i.e., feedforward), whereas various recurrent neural network architectures  ... 
arXiv:2012.12351v2 fatcat:mk5lynyluzaq5izgayaschxmzy

Front Matter: Volume 11459

Dmitry E. Postnov
2020 Saratov Fall Meeting 2019: Computations and Data Analysis: from Nanoscale Tools to Brain Functions  
-35] THEORETICAL BIOPHYSICS AND NONLINEAR DYNAMICS 0V Interaction of bistable neurons leading to the complex network dynamics 11459 0W Control of dynamics of bistable neural network by an external  ...  11459 04 Features of motor-related brain activity revealed via recurrence quantification analysis 11459 05 Using artificial neural networks for classification of kinesthetic and visual imaginary movements  ... 
doi:10.1117/12.2570907 fatcat:cgi74uiacngljlhshdwj7pz4u4

An Overview of Deep Learning Algorithms and Their Applications in Neuropsychiatry

Gokhan Guney, Busra Ozgode Yigin, Necdet Guven, Yasemin Hosgoren Alici, Burcin Colak, Gamze Erzin, Gorkem Saygili
2021 Clinical Psychopharmacology and Neuroscience  
In this review, we aim to summarize the most common DL algorithms and their applications in neuropsychiatry and also provide an overview to guide the researchers in choosing the proper DL architecture  ...  With the advance of new sensors, data storage, and processing hardware, DL algorithms start dominating various fields including neuropsychiatry.  ...  networks (CNNs), recurrent neural networks (RNNs) and generative adversarial networks (GANs).  ... 
doi:10.9758/cpn.2021.19.2.206 pmid:33888650 pmcid:PMC8077051 fatcat:wiycvc4lffhdhh5ehi6jkn7nyi

Can Biological Quantum Networks Solve NP-Hard Problems?

Göran Wendin
2019 Advanced Quantum Technologies  
On the other hand, artificial intelligence and machine learning implemented in complex dynamical systems based on genuine quantum networks can certainly be expected to show enhanced performance and quantum  ...  advantage compared with classical networks.  ...  One can view a large nonlinear recurrent neural network as an implementation of such a kernel, where the network response to an input corresponds to the kernel output [14] .  ... 
doi:10.1002/qute.201800081 fatcat:nud3r5wn3zbwbknq7hvbwamye4

Multiscale Neural Modeling of Resting-state fMRI Reveals Executive-Limbic Malfunction as a Core Mechanism in Major Depressive Disorder [article]

Guoshi Li, Yujie Liu, Yanting Zheng, Ye Wu, Danian Li, Xinyu Liang, Yaoping Chen, Ying Cui, Pew-Thian Yap, Shijun Qiu, Han Zhang, Dinggang Shen
2020 medRxiv   pre-print
To overcome this limitation, we significantly improved a previously developed Multiscale Neural Model Inversion (MNMI) framework that can link mesoscopic neural interaction with macroscale network dynamics  ...  on resting-state fMRI with a relatively large sample size.  ...  proposed MNMI model is directly applicable to rs-fMRI, incorporates realistic neural population 352 dynamics, and enables independent estimation of individual EC links.  ... 
doi:10.1101/2020.04.29.20084855 fatcat:oiygy5iz2nbozn7yt7ajmat7ky

Estimation and Validation of Individualized Dynamic Brain Models with Resting State fMRI

Matthew F. Singh, Todd S. Braver, Michael W. Cole, ShiNung Ching
2020 NeuroImage  
We aim to bridge this gap through the development of a new modeling approach termed Mesoscale Individualized Neurodynamic (MINDy) modeling, wherein we fit nonlinear dynamical systems models directly to  ...  A key challenge for neuroscience is to develop generative, causal models of the human nervous system in an individualized, data-driven manner.  ...  Like current neural-mass models, MINDy employs a nonlinear dynamical systems model which is capable of generating long-term patterns of brain dynamics.  ... 
doi:10.1016/j.neuroimage.2020.117046 pmid:32603858 pmcid:PMC7875185 fatcat:c2sbnfd2jraexdrfazppk74faa

Cortical response to naturalistic stimuli is largely predictable with deep neural networks

Meenakshi Khosla, Gia H. Ngo, Keith Jamison, Amy Kuceyeski, Mert R. Sabuncu
2021 Science Advances  
Furthermore, we illustrate that encoding models learn high-level concepts that generalize to task-bound paradigms.  ...  Encoding models that predict neural responses to arbitrary stimuli can be very useful for studying brain function.  ...  DNNs fail to capture known properties of biological networks such as local recurrence; however, they have been found to be useful for modeling neural activity across different sensory systems.  ... 
doi:10.1126/sciadv.abe7547 pmid:34049888 pmcid:PMC8163078 fatcat:jh6hpfzbznbmvpy3yy2oftfkbu

2020 Index IEEE Transactions on Fuzzy Systems Vol. 28

2020 IEEE transactions on fuzzy systems  
., An Optimized Type-2 Self-Organizing Fuzzy Logic Controller Applied in Anesthesia for Propofol Dosing to Regulate BIS; TFUZZ June 2020 1062-1072 Weinstein, A., see Veloz, A., TFUZZ Jan. 2020 100-111  ...  ., +, TFUZZ Aug. 2020 1519-1530 Convolutional neural nets Fast Training Algorithms for Deep Convolutional Fuzzy Systems With Application to Stock Index Prediction.  ...  ., +, TFUZZ Feb. 2020 273-287 Adaptive Event-Triggered Fuzzy H 3 Filter Design for Nonlinear Networked Knowledge based systems A Generalized Heterogeneous Type-2 Fuzzy Classifier and Its Industrial Application  ... 
doi:10.1109/tfuzz.2020.3048828 fatcat:vml5fun6szcqbhpceebk3xfg2u

Dynamic Causal Models and Autopoietic Systems

2007 Biological Research  
Autopoiesis and related formal theories of biological systems as autonomous machines represent a body of concepts with many successful applications.  ...  Dynamic Causal Modelling (DCM) and the theory of autopoietic systems are two important conceptual frameworks.  ...  ACKNOWLEDGEMENTS I am much indebted to Francisco Varela and Karl Friston, who have initiated most of the ideas developed here, for their support during my doctoral and postdoctoral trainings.  ... 
doi:10.4067/s0716-97602007000500010 fatcat:gwrf6ruf7nf57c5dzsrj2vbg4a

fMRI Brain Decoding and Its Applications in Brain–Computer Interface: A Survey

Bing Du, Xiaomu Cheng, Yiping Duan, Huansheng Ning
2022 Brain Sciences  
With the great success of deep learning on image recognition and generation, deep neural networks (DNN) have been engaged in reconstructing visual stimuli from human brain activity via functional magnetic  ...  Furthermore, brain neural-activity-decoding-enabled fMRI-based BCI applications in mental and psychological disease treatment are presented to illustrate the positive correlation between brain decoding  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable.  ... 
doi:10.3390/brainsci12020228 pmid:35203991 pmcid:PMC8869956 fatcat:t664eccq6nh5plnvhac2r2gcpa
« Previous Showing results 1 — 15 out of 1,548 results