Filters








13,663 Hits in 4.9 sec

On general systems with randomly occurring incomplete information

Zidong Wang, Jun Hu, Hongli Dong
2016 International Journal of General Systems  
are taken into account in the framework of discrete-time memristive recurrent neural networks for the first time.  ...  In the paper entitled "H ∞ State Estimation for Discrete-time Memristive Recurrent Neural Networks with Stochastic Time-delays" by H.  ... 
doi:10.1080/03081079.2015.1106734 fatcat:3uvg6qgeu5bipn7cbon3lfovyy

Attractive Periodic Sets in Discrete-Time Recurrent Networks (with Emphasis on Fixed-Point Stability and Bifurcations in Two-Neuron Networks)

Peter Tiňo, Bill G. Horne, C. Lee Giles
2001 Neural Computation  
Finally, for an N-neuron recurrent network, we give lower bounds on the rate of convergence of attractive periodic points toward the saturation values of neuron activations, as the absolute values of connection  ...  We perform a detailed xed-point analysis of two-unit recurrent neural networks with sigmoid-shaped transfer functions.  ...  Hirsch (1994) has pointed out that while there is a saturation result for stable limit cycles of continuous-time networks-for suf ciently high gain, the output along a stable limit cycle is saturated  ... 
doi:10.1162/08997660152002898 pmid:11387050 fatcat:riuiczchvnbzrbqnmycyu2w3ui

Learning accurate path integration in a ring attractor model of the head direction system [article]

Pantelis Vafidis, David Owald, Tiziano D'Albis, Richard Kempter
2021 bioRxiv   pre-print
with different gains.  ...  The mature network is a quasi-continuous attractor and reproduces key experiments in which optogenetic stimulation controls the internal representation of heading, and where the network remaps to integrate  ...  reaching saturation. 1206 Additionally, because the recurrent input is filtered in time (Eq.  ... 
doi:10.1101/2021.03.12.435035 fatcat:illqgsybfnejfneful6uklefyi

Learning accurate path integration in ring attractor models of the head direction system

Pantelis Vafidis, David Owald, Tiziano D'Albis, Richard Kempter
2022 eLife  
with different gains in rodents.  ...  The mature network is a quasi-continuous attractor and reproduces key experiments in which optogenetic stimulation controls the internal representation of heading, and where the network remaps to integrate  ...  The funding sources were not involved in study design, data collection and interpretation, or the decision to submit the work for publication.  ... 
doi:10.7554/elife.69841 pmid:35723252 pmcid:PMC9286743 fatcat:25ypm4hebbcw3oiqzp3upmlco4

Coherent Neural Networks and Their Applications to Control and Signal Processing [chapter]

Akira Hirose
1999 World Scientific Series in Robotics and Intelligent Systems  
All operations are synchronous at discrete time steps. The amplitude constant A in (5) is chosen at A = 1 :0 [19] .  ...  The neuron number N , discrete phase number L, saturation amplitude A, and neuron gain g is 50, 8, 1, and 10, respectively, in this experiment.  ... 
doi:10.1142/9789812816528_0014 fatcat:hm5vt2nucnag3inn4eeokmcfzm

Cellular neural network as a non-linear filter of impulse noise

Elena Solovyeva
2017 2017 20th Conference of Open Innovations Association (FRUCT)  
Feedforward discrete-time cellular neural network for filtering of impulse noise from two-dimensional (image) signals is represented.  ...  It is shown that the cellular neural network surpasses median filter, Volterra filter and perceptron neural network in accuracy of image restoration and in simplicity of filter implementation.  ...  x n x n dt t where n is the discrete normalized time.  ... 
doi:10.23919/fruct.2017.8071343 dblp:conf/fruct/Solovyeva17 fatcat:xkbfjgz4rbhyfkjduizgxwmwli

DR-RNN: A deep residual recurrent neural network for model reduction [article]

J.Nagoor Kani, Ahmed H. Elsheikh
2017 arXiv   pre-print
We introduce a deep residual recurrent neural network (DR-RNN) as an efficient model reduction technique for nonlinear dynamical systems.  ...  We also show significant gains in accuracy by increasing the depth of proposed DR-RNN similar to other applications of deep learning.  ...  Standard Recurrent Neural Network Recurrent Neural Network (RNN) is a neural network that has at least one feedback connection in addition to the feedforward connections [28] .  ... 
arXiv:1709.00939v1 fatcat:lrvy22vxnvfxdeb4yitz2if2ta

Noise Tolerance of Attractor and Feedforward Memory Models

Sukbin Lim, Mark S. Goldman
2012 Neural Computation  
An online supplement is available at  ...  networks can amplify signals they receive faster than noise accumulates over time.  ...  This research was conducted in the absence of any commercial or financial relationships that could be constructed as a potential conflict of interest.  ... 
doi:10.1162/neco_a_00234 pmid:22091664 pmcid:PMC5529185 fatcat:s32tvgjzbrdezebw6sus65so24

Stability of discrete memory states to stochastic fluctuations in neuronal systems

Paul Miller, Xiao-Jing Wang
2006 Chaos  
We will first discuss a strongly recurrent cortical network model endowed with feedback loops, for short-term memory.  ...  For the neuronal network we report interesting ramping temporal dynamics as a result of sequentially switching an increasing number of discrete, bistable, units.  ...  In a recurrent network, this allows for a DOWN state that is not silent, in fact with a firing rate as high as 10 Hz in our case.  ... 
doi:10.1063/1.2208923 pmid:16822041 pmcid:PMC3897304 fatcat:4zh6cs2nr5b33b2ckgdphlpoy4

Modulating the granularity of category formation by global cortical states

Yihwa Kim
2008 Frontiers in Computational Neuroscience  
We show that a competitive network, shaped by recurrent inhibition and endowed with Hebbian and homeostatic synaptic plasticity, can enforce stimulus categorization.  ...  The degree of competition is internally controlled by the neuronal gain and the strength of inhibition.  ...  ACKNOWLEDGEMENTS We would like to acknowledge Stefano Fusi for his continuing support, especially in the initial phase of the work, for many inspiring discussions, IT network (20 × 20 neurons) to all  ... 
doi:10.3389/neuro.10.001.2008 pmid:18946531 pmcid:PMC2525940 fatcat:7q6boz72v5csdftkgzy6ayozsy

DESIGN AND LEARNING WITH CELLULAR NEURAL NETWORKS

JOSEF A. NOSSEK
1996 International journal of circuit theory and applications  
This is of course also true in the case of continuous-time and discrete-time cellular neural networks (CT-CNNs and DT-CNNs), where the local and translationally invariant interconnections are put together  ...  Here the discretization of space (and time) plays a central role in arriving at a set of ODES (or difference equations), which can be easily mapped onto a CT-CNN (or DT-CNN).5 Of utmost importance is to  ... 
doi:10.1002/(sici)1097-007x(199601/02)24:1<15::aid-cta900>3.0.co;2-5 fatcat:zxz3svirlvdbjbh75fcz2a4bpm

Computation in Dynamically Bounded Asymmetric Systems

Ueli Rutishauser, Jean-Jacques Slotine, Rodney Douglas, Olaf Sporns
2015 PLoS Computational Biology  
Previous explanations of computations performed by recurrent networks have focused on symmetrically connected saturating neurons and their convergence toward attractors.  ...  This inherent boundedness permits the network to operate with the unstably high gain necessary to continually switch its states as it searches for a solution.  ...  This signal restoration is achieved by extremely high gain, so that a small input bias will drive the node into saturation at one of its two voltage limits.  ... 
doi:10.1371/journal.pcbi.1004039 pmid:25617645 pmcid:PMC4305289 fatcat:nrxl3yo74jgbvgteoelnwcnjqm

Learning to Generate Compositional Color Descriptions [article]

Will Monroe, Noah D. Goodman, Christopher Potts
2016 arXiv   pre-print
We present an effective approach to generating color descriptions using recurrent neural networks and a Fourier-transformed color representation.  ...  ), and compositional phrases ("faded teal") not seen in training.  ...  This research was supported in part by the Stanford Data Science Initiative, NSF BCS 1456077, and NSF IIS 1159679.  ... 
arXiv:1606.03821v2 fatcat:pn256zcksvc5hismwpr2e7qxpu

Learning to Generate Compositional Color Descriptions

Will Monroe, Noah D. Goodman, Christopher Potts
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
We present an effective approach to generating color descriptions using recurrent neural networks and a Fouriertransformed color representation.  ...  ), and compositional phrases ("faded teal") not seen in training.  ...  This research was supported in part by the Stanford Data Science Initiative, NSF BCS 1456077, and NSF IIS 1159679.  ... 
doi:10.18653/v1/d16-1243 dblp:conf/emnlp/MonroeGP16 fatcat:nlgku4tlrbgbpp7dwz3zq74twy

Table of contents

2020 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS)  
Xin Song 314 Discrete-time Recurrent Neural Network for Solving Discrete-form Time-variant Complex Division ………..………………………………….……...  ...  ……Jian Liu, Xiaoe Ruan, Yamiao Zhang 486 Iterative Learning Control for Multiple Time-Delays Discrete Systems in Finite Frequency Domain …………...……………………………………......  ... 
doi:10.1109/ddcls49620.2020.9275156 fatcat:kl3b4ptikjhzjn6p7eoqcmwypa
« Previous Showing results 1 — 15 out of 13,663 results